US4720780A - Memory-linked wavefront array processor - Google Patents

Memory-linked wavefront array processor Download PDF

Info

Publication number
US4720780A
US4720780A US06/777,112 US77711285A US4720780A US 4720780 A US4720780 A US 4720780A US 77711285 A US77711285 A US 77711285A US 4720780 A US4720780 A US 4720780A
Authority
US
United States
Prior art keywords
memory
processing element
array
processor
processing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US06/777,112
Inventor
Quentin E. Dolecek
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Johns Hopkins University
Original Assignee
Johns Hopkins University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Johns Hopkins University filed Critical Johns Hopkins University
Assigned to JOHNS HOPKINS UNIVERSITY THE, BALTIMORE, MARYLAND, A CORP OF MARYLAND reassignment JOHNS HOPKINS UNIVERSITY THE, BALTIMORE, MARYLAND, A CORP OF MARYLAND ASSIGNMENT OF ASSIGNORS INTEREST. Assignors: DOLECEK, QUENTIN E.
Priority to US06/777,112 priority Critical patent/US4720780A/en
Priority to PCT/US1986/001903 priority patent/WO1987001841A1/en
Priority to DE8686906519T priority patent/DE3685107D1/en
Priority to JP61505584A priority patent/JPS63501530A/en
Priority to EP86906519A priority patent/EP0237571B1/en
Priority to KR1019870002221A priority patent/KR970001899B1/en
Priority to US07/144,193 priority patent/US4922418A/en
Publication of US4720780A publication Critical patent/US4720780A/en
Application granted granted Critical
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • G06F15/76Architectures of general purpose stored program computers
    • G06F15/80Architectures of general purpose stored program computers comprising an array of processing units with common control, e.g. single instruction multiple data processors
    • G06F15/8046Systolic arrays
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • G06F15/16Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/163Interprocessor communication
    • G06F15/173Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
    • G06F15/17356Indirect interconnection networks
    • G06F15/17368Indirect interconnection networks non hierarchical topologies
    • G06F15/17381Two dimensional, e.g. mesh, torus

Definitions

  • the invention relates to an array processor having a unique architecture for computing a broad range of signal processing, scientific, and engineering problems at ultra-high speed. More particularly, the invention called a Memory-Linked Wavefront Array Processor (MWAP) comprises a computing architecture that provides global asynchronous communication within the processing array and also provides local/data driven asynchronous control of each processing element.
  • MWAP Memory-Linked Wavefront Array Processor
  • the systolic array introduced by H. T. Kung (see, H.T. Kung, "Let's Design Algorithms for VLSI Systems", in Prac. Caltech Conf. VLSI, Jan. 1979, pp. 66-90), is an array of processors that are locally connected and operate synchronously on the same global clock. Algorithms are executed in a pulsed (systolic flow) fashion. That is, the network of processors rhythmically compute and pass data through the system.
  • the systolic array has the properties of modularity, regularity, local interconnection, and highly pipelined, highly synchronized multiprocessing. However, it requires global synchronization. That is, data movement is controlled by a global timing-reference. In order to synchronize the activities in a systolic array, extra delays are often used to ensure correct timing. For large arrays of processors, synchronization of the entire computing network becomes intolerable or even impossible.
  • the systolic array is not programmable; each algorithm requires a separate and distinct array configuration.
  • the systolic array can be made "hardware programmable" by using matrix switches to reconfigure the array geometry. In any case, the systolic array always requires a direct mapping of the computation algorithm onto physical processor elements.
  • the wavefront array processor uses the same geometric structures as the systolic array and is generally described in: S.Y. Kung et al, "Wavefront Array Processor: Architecture, Language and Applications", MIT Conf. on Advanced Research in VLSI, Jan. 1982, MIT, Cambridge, MA. It differs from the systolic array in that control flows through the array along with data and parameters. This addition of local control flow to local data-flow permits data-driven, self-timed processing. Conceptually, the requirement of correct "timing" is replaced by the requirement for correct "sequencing".
  • Every processor element (PE) in a wavefront array processor has a bidirectional buffer with independent status flags for each adjacent PE.
  • the flow of data is asynchronous between PE's with control tokens sent between PE's to determine data availability and data use. This relaxes the strict timing requirement of the systolic array, simplifies algorithm development, and often results in faster algorithms and processing speed.
  • the wavefront processor thus operates by passing control and data between processors in a wavelike fashion so that computation flows from one processor to the next as each processor completes a recursion (step) in the algorithm.
  • FFT Fast Fourier Transform
  • the present invention called a Memory-Linked Wavefront Array Processor (MWAP), extends the wavefront array processor to handle global-type communication.
  • MWAP Memory-Linked Wavefront Array Processor
  • the memory-linked wavefront array processor relaxes the requirement for strict local communication dictated by the prior art, and therefore permits implementation of the FFT algorithm using the recursion formula.
  • This invention also enlarges the computation power and flexibility of array processors by relaxing the prior art requirement of passing data between the processing elements in the order in which that data is to be used by the receiving processing element.
  • the MWAP utilizes a new array processing architecture which can compute a broad range of signal processing, scientific, and engineering problems at ultra-high speed.
  • the invented MWAP architecture comprises an array of identical programmable processing elements linked together by dual-port memory linking elements that contain a set of special purpose control flags. All communication in the network is done asynchronously via these linking memory elements. Data driven/local control is obtained by using asynchronous handshaking between the processing elements and the dual-port memory linking elements. Moving the asynchronous link to the dual-port memory linking elements permits the use of sequence control "tokens" to be replaced by hardware control flags in each memory linking element.
  • Each processing element is capable of simultaneous arithmetic computation, communication in two directions, logic decisions, and program control modification.
  • the MWAP has the properties of modularity, regularity, local interconnection, and highly pipelined multiprocessing. Later in this Specification, computation of algorithms using the MWAP architecture are compared to those used for typical prior art systolic and wavefront array processors to illustrate some of the unique capabilities and properties of the MWAP architecture. In general, the MWAP is shown to provide higher throughput rates for most algorithms, to extend the range of algorithms that can be implemented on array processors, and to permit a single linear array configuration to be programmed for a wide variety of algorithms that could previously only be handled on more complex two dimensional prior art systolic and wavefront arrays.
  • a first novel feature of the invention is to provide global asynchronous communication within an array of processing elements by linking together adjacent processing elements via asynchronous dual-port memory linking elements.
  • a second novel feature of the invention is that data can be passed between processing elements in any desired order not restricted by the order that data is to be used by the receiving processing element.
  • a third novel feature of the invention is that coefficients and other information or data used in calculating an algorithm can be stored in the dual-port memory linking elements between processing stages in an array processor.
  • a fourth novel feature of the invention is that data-driven/local control of each processing elements is obtained using asynchronous handshaking between each processing element and the dual-port memory linking element located adjacent in the array.
  • a fifth novel feature of the invention is that moving the asynchronous link to the memory linking elements, permits software sequence control "tokens" to be replaced by hardware control flags located in the memory linking elements.
  • a sixth novel feature of the invention is that the processing operation of a particular processing element is suspended when it attempts to access a memory location in the adjacent dual-port memory linking element until such time as a control flag associated with such memory location has been set by another processing element adjacent to the particular dual-port memory linking element.
  • each particular processing element has an internal control and bus arrangement which permits simultaneous communication with its adjacent dual-port memory linking elements in the processing array.
  • each processing element can multiply, add or subtract, read or write to its left adjacent memory linking element and read or write to its right adjacent memory linking element, in a linear array, all during the same instruction cycle.
  • a ninth novel feature of the present invention is that data and computation can be propagated to the right or left in a linear array or to the right or left or up or down in a two dimensional array.
  • a tenth novel feature of the present invention is that each processing element in the MWAP can store several different program sequences for computing different algorithms, so that different processing elements in an array can perform different computations or the same processing element can perform different computations at different times during the computation cycles.
  • FIG. 1 illustrates the general architecture of prior art array processors, FIG. 1A illustrating a linear array and FIG. 1B illustrating a 3 ⁇ 3 square array;
  • FIG. 2 is a block diagram illustrating a linear array Memory-Linked Wavefront Array Processor, as taught by the present invention
  • FIG. 3 is a block diagram illustrating a two-dimensional geometric array structure for the Memory-Linked Wavefront Array Processor, as taught by the present invention
  • FIG. 4 is a block diagram of a processing element used in a linear MWAP array
  • FIG. 5 is a block diagram of a processing element used in a two-dimensional MWAP array
  • FIG. 6 is a detailed block diagram illustrating the internal register and bus arrangement for a typical processing element in the MWAP;
  • FIG. 7 is the sequencer block diagram for a typical MWAP processing element
  • FIG. 8 is a block diagram showing the internal structure of a dual-port memory linking element used in the MWAP architecture
  • FIG. 9 is a flow diagram illustrating the FIR filter processing sequence for a MWAP
  • FIG. 10 illustrates the use of a MWAP data loop back to calculate multiple points in the 1-D heat conduction equation
  • FIG. 11 illustrates the use of a MWAP for simultaneous computation of multiple points in the 1-D heat conduction equation
  • FIG. 12 illustrates the use of a two dimensional MWAP to compute partial differential equations with variable coefficients
  • FIG. 13 illustrates the use of a prior art broadcast array for full-matrix multiplication
  • FIG. 14 illustrates the use of a prior art hex-connected systolic array to compute matrix multiplication
  • FIG. 15 illustrates the use of a prior art wavefront array to compute matrix multiplication
  • FIG. 16 illustrates the use of a linear MWAP array to compute matrix multiplication as taught by the present invention
  • FIG. 17 is a flow diagram illustrating the computation sequence for a 3 ⁇ 3 matrix multiplication using the linear MWAP array shown in FIG. 16;
  • FIG. 18 illustrates the shuffle-exchange needed to compute the Fourier Transform using the recursion formula
  • FIG. 19 illustrates the computation sequence used by a MWAP to compute the Fourier Transform using the recursion formula.
  • the MWAP uses a modular structure for both the processing hardware and for programming the system.
  • the system architecture can be implemented with a linear processing array, a two-dimensional processing array, or an n-dimensional processing array, where n is an integer (NOTE: because the MWAP does not require a global clock like the systolic array processor, propagation delays won't limit the size of the array.)
  • the basic linear MWAP array architecture shown in FIG. 1, consists of a host interface 10 operably connected to a dual port memory linking element 12, multiple processing element/dual port memory linking element pairs 14, and a host output interface 16.
  • the dual port memory linking element may be composed of memory chips or a set of registers.
  • Asynchronous local communication is provided between each processing element and its adjacent dual port memory linking elements. Data, coefficients used in calculations, intermediate calculations and/or other information can be stored in selected memory locations in each dual port memory linking element.
  • Asynchronous communication between processing elements occurs, for example, as data and other information is written into a memory location in dual port memory linking element 22, by one processing element 20, and is acquired, after appropriate handshaking, by another adjacent processing element 24.
  • processing element 20 is not required to write data into the dual port memory linking element 22 in the same order that data is used by the receiving processing element 24.
  • processing element 24 may pass through data or information from the adjacent dual port memory element 22 to adjacent dual port memory 26 without processing the data or information, and allowing a downstream processing element to acquire that data or other information for its processing purposes.
  • the prior art array processing architecture is shown in FIG. 1, contains an array of processing elements 28 which are directly interconnected. Memory blocks 30 are located external to the processing array and along its edges. As will be shown later in the Specification, many algorithm computations are difficult and cumbersome with the prior architecture.)
  • each processing element may access memory locations in a right adjacent dual port memory element and a left adjacent dual port element. Therefore, the asynchronous local communication provided via the dual port memory linking elements makes available global communication within the processing array.
  • linking the processing elements with dual port memory linking elements provides the following advantages: (1) global communications; (2) data and computation can be propagated to the right or left; (3) the distance between data elements can increase or decrease between processing stages; (4) coefficients and other information can be stored between processing stages during an initialization phase; and, (5) both single and two-dimensional algorithms can be processed using a linear array.
  • a hardware control flag located in the dual port memory element can replace a software control token. This feature, which shall be described later, allows data driven/local control to be obtained using asynchronous hardware handshaking between a processing element and its adjacent dual port memory linking elements.
  • FIG. 3 is a block diagram illustration of the basic MWAP architecture for a two-dimensional processing array.
  • dual port memory linking elements 32 are interspersed between processing elements 34 in the array.
  • a processing element 34 may have direct access to adjacent dual port memory linking elements to its right and left as well as up and down in the array.
  • Processing element 32 and dual port memory linking element 34 in the two-dimensional array operate similar to those elements in the linear array.
  • the basic MWAP architecture can be extended by application of this invention to any n-dimensional array. It is further within the scope of the present invention to use n-port memory linking elements and n-port processing elements, where n is greater than two.
  • FIG. 4 is a block diagram illustrating one embodiment of the modular processing element, as taught by the present invention for use in a linear MWAP array.
  • the processing element can be separated into three sections: the arithmetic section (elements 36, 38, 40), the addressing registers (elements 42, 44), and the program flow control block (or control logic, elements 46, 48).
  • the arithmetic section consists of two arithmetic processors (36, 40), internal arithmetic registers 38, and associated data bus structure.
  • the address registers consist of a group of eight counter/register pairs (42, 44) for each memory port the processing element can access.
  • FIG. 4 shows two groups of address registers so that each processing element can access dual-port memory linking elements to its right and left (see FIG.
  • Address registers 42 are used to address memory locations in the right adjacent dual-port memory linking element; and address registers 44 are used to address memory locations in the left adjacent dual-port memory linking element.
  • the control logic section contains a program memory 46 and associated logic 48 to make the processing element programmable.
  • Control unit 48 senses and either sets or resets hardware control flags in the right adjacent dual port memory linking element via line 50, and in the left adjacent dual port memory linking element via line 52. Control unit 48 will suspend operation of the processing element when the program sequence calls for one of the address registers (42, 44) to access its adjacent dual port memory element and a control flag in that dual port memory element associated with that memory field (or associated with that particular address register) remains down. The control unit will continue to suspend activity of the processing element until that particular flag in the adjacent dual port memory linking element has been set by the other processing element adjacent to the particular dual port memory linking element. In this way, the processing unit is self-timing and will remain inactive until the required data is available. Thus, each processing element will have asynchronous data driven local control.
  • Each control flag in the dual port memory linking elements have two states, and the control unit in the adjacent processing elements are programmed so that when a flag is in a particular state it will appear to be a set flag to one of the adjacent processing elements and a reset flag to the other adjacent processing element.
  • the invented architecture may use two or more registers to access different data locations in a particular adjacent dual port memory linking element. Since each dual port memory element may have two or more control flags (each control flag associated with an address register in said adjacent dual port memory element), memory overlapping is possible.
  • a processing element to the right of a particular dual port memory linking element may read or write data using one of its address registers from a first location in a particular dual port memory element and a processing element to the left of that particular dual port memory element may simultaneously read or write data into a second memory location in that dual port memory element.
  • flag 1 located in the dual port memory element and associated with the first memory location
  • flag 2 also located in the dual port memory
  • the processing element can read or write from the left dual port memory from bus 62, while simultaneously reading or writing from the right dual port memory means from bus 60.
  • the internal bus arrangement 64, 66
  • instruction words stored in the program memory 46 have separate fields to control read/write operations from the right port 60 and said left port 62.
  • a read or write to the left port and a read or write to the right port may all occur in the same instruction cycle.
  • the instruction words stored in program memory 46 have separate fields to control the multiplier, adder, and left and right data port addresses. Since these operations can occur in parallel, a multiply, add or subtract, or a read or write to the left port, and a read or write to the right port may all occur in the same instruction cycle.
  • FIG. 5 is a block diagram illustrating one embodiment of a processing element for use in a two-dimensional processing array.
  • the basic processing element used in the linear array (see FIG. 4) is similar to that used for a two-dimensional array; except that processing element 67 has four separate sets of address registers (42, 44, 68 and 70) to access adjacent dual port memory lining elements located to the right, left, and up and down in the two dimensional array from the processing element.
  • four control lines 72 sense and set or reset hardware control flags in the adjacent right, left, up and down dual port memory linking elements.
  • FIG. 6 represents a more detailed block diagram of the modular processing element as taught by the present invention.
  • FIG. 6 shows a processing element used in a linear array.
  • FIG. 6 it is to be understood that it is within the scope of this invention to extend the particular structure shown in FIG. 6 to any multi-dimensional array.
  • the processing element consists of: a control unit 74 having an instructional cache and program sequencer; a block of memory address registers 76 to address adjacent dual port memory linking elements (not shown) along right address bus 78 and left address bus 80; a floating point multiplier 82; a floating point arithmetic section (ALU) 84; input registers 86; output registers 88; and, internal arithmetic registers 90.
  • the output registers 88, input registers 86, and internal arithmetic registers 90 are each separately connected to right output bus 92, right input bus 94, left output bus 96 and left input bus 98.
  • Input/output buses (92, 94) are operably coupled to the right dual port memory linking element and input/output buses (96, 98) are operably coupled to the left dual port memory linking element.
  • the arithmetic section consists of fourteen arithmetic registers (label R0 through R13 in FIG. 6), a floating point multiplier 82 and, a floating point adder/subtracter 84.
  • the registers 90 are connected using a specialized bus structure designed to support multiply and accumulation algorithms. Only two registers (R0 and R13) are connected to both the left and right input buses (94, 98) and both output buses (92, 96). Six registers are attached to input buses only (R1, R2, R4, R6, R9 and R11), and four are available to output buses only (R7, R8, R12 and R13). Two registers, R5 and R10, are not connected to any input or output bus. This structure supports efficient real and complex number operations with a minimal number of registers and interconnects.
  • the multiplier, adder/subtracter, left and right data ports are independently controlled by separate fields in the processing element instruction words. Since the separate instruction fields allow these operations to occur in parallel, a multiply, an addition or subtraction, and read/write by to the left port, or read/write to the right port, may all occur in the same instruction cycle.
  • the addressing section consists of two groups (100, 102) of eight counter/register pairs.
  • One group 102 serves as the left address counters (LAC0 to LAC7) and the other group 100 serves as the right address counters (RAC0 to RAC7).
  • a base register 104 Associated with each address counter is a base register 104. This base register is used to hold a reference memory address for the counters.
  • a counter 106 that supplied the address can be incremented, or reset to the value in its base address register, or the counter can remain unchanged.
  • the outputs of address counters LAC6, LAC7, RAC6 and RAC7 are placed on the address bus in bit reverse order. The transform size associated with this bit reversal is programmable.
  • FIG. 7 An expanded block diagram of the programming sequence section 74 is shown in FIG. 7. It contains a program memory 112, a program address counter 114, and four program branch address registers 116. In addition, there are two looping counters 118, 120 (LOOP 1 and LOOP 2) that are used for conditioning branching out of the loops. The base register (122, 124) are attached to each counter for resetting the loop count. One counter can be modified during each instruction cycle. It can be either incremented, decremented or reloaded from its base register. In addition to these loop counters, arithmetic register 112 (see FIG. 6) can be used for conditional branching. This allows conditioning branching that is data dependent.
  • FIG. 8 is a block diagrammatic view of the dual port memory linking element as taught by the present invention.
  • the dual port memory linking element has two unique features: (1) it is asynchronously driven at its boundary, and (2) it contains two flags 126. Data flow in the MWAP is controlled by these flags. These flags are used to indicate the availability of data to an adjacent processing element. Any instruction that uses LAC0 or RAC0 (see FIG. 6) in the processing element as the address for memory access is not executed unless control flag 1 in the associated dual port memory linking element is set. If an instruction of this type attempts execution when flag 1 is not set, the instruction execution halts until access is permitted by the setting by the control flag. When the flag is set, the instruction execution begins.
  • flag 2 controls the execution of instructions referencing LAC 1 and RAC 1 (see FIG. 6).
  • the address register 142 on the right port of the dual-port memory linking element would connect to bus 76
  • the input data fifo 140 and output data fifo 138 would respectively be connected to buses 98 and 96 and the right port handshake logic 136 would connect to control lines 108.
  • address register 134, input data fifo 132, output data fifo 130 and handshaking logic 128 associated with the left port of the dual port memory linking element would connect to similar elements in a processing element located to its left.
  • Static RAM memory 136 can therefore be accessed by the processing element to its adjacent left and its adjacent right. As discussed previously, with the use of two control flags, the adjacent processing elements can have overlapping access to different portions of static RAM 136. This would enable to left adjacent processing element and the right adjacent processing element simultaneous access to different portions of static RAM 136.
  • each Processing Element (PE) in the MWAP computes one term of the wavefront b(k)x(i), and forwards the input x(i) and partial sum to the next PE.
  • the first PE reads the input data stream and the last PE sends the output Y(i) to the host computer or system bus.
  • the FIR algorithm is calculated using the linear array shown in FIG. 9; and the sequence of events is also illustrated for several processing cycles in FIG. 9. Cycles 1 and 2 essentially inialize the array. (The notation > indicates the direction data is being read or written, for example, in cycle 1, data x(0) is being read from DPM #1 and in cycle #2 data x(2) is being written into DPM2).
  • processing element #1 reads x(1) from the memory to its left, computes the b(2)x(1) term, and writes both x(1) and the previous product b(2)x(0) into the memory to its right, using the base address specified by memory address register #1.
  • PE #1 completes storing the partial sum and x(1) in the memory to its right, it sets control flag #1 in that memory to notify PE #2 that data is ready for it to process. (Note:the notation #1 and #2 connected to an arrow indicates the setting and resetting of Flag 1 and 2, respectively.)
  • PE #1 then repeats the process for x(2) using memory address register #2 and control flag #2. This sequence is repeated using first address register #1 and control flag #1 and then address register #2 and control flag #2 to process all input samples x in the left memory. If the host is continuously entering new data samples into the left most memory, the MWAP can continuously filter the input data forever.
  • processing element #2 When the control flag #1 is set, processing element #2 reads x(n) and the partial sum from the memory to its left. It then resets control flag #1, to permit PE #1 to use that section of the memory again, and adds the product b(1)x(n+1) term to the partial sum to obtain the new partial sum b(2)x(n)+b(1)x(n+1).
  • the data sample x(n) and the previous partial sum is written into the memory to its right, using the base address specified by its memory address register #1.
  • PE #2 completes storing the partial sum and x(n) in the memory to its right, it sets the control flag #1 in that memory to notify PE #3 that data is ready for it to process.
  • PE #2 then repeats the process for x(n+1) using its memory address register #2 and control flag #2 in the memory to its left; setting control flag #2 in the memory to its right. The sequence is repeated over and over just as with the first processing element.
  • Processing element #3 reads the partial sum and x from the memory to its left, adds the product b(0)x(n+2) to the partial sum and puts the answer in the memory to its right using the same sequence of memory address registers and control flags as described for processing elements #1 and #2. Thus, the results Y(0), Y(1), . . . are written into the right-most dual port memory for reading by the host computer.
  • the FIR processing sequence illustrates several properties of the Memory-Linked Wavefront Array Processor:
  • the MWAP is self-timing (there is no need for a global clock controlling the individual PEs), i.e., the flow of computations is controlled by the two flags in each dual port memory.
  • the use of two control flags permits overlapping of data buffers (e.g., the PE to the right and left of a dual-port memory linking element can simultaneously access different memory locations in that dual-port memory linking element).
  • two control flags generally permit efficient processing of any MWAP algorithm.
  • the MWAP throughput rate depends only on the number of processing elements/linking memory pairs used and the algorithm implemented; not on the size of the data set processed or the length of the computation. For example, the MWAP throughput rate does not change for longer (more stages) FIR filters if one additional PE/Memory linking pair is used for each additional stage in the filter.
  • the same algorithm used for the FIR filter on the MWAP can be used to solve a single point, n, in the 1-D heat equation with each interaction of the MWAP.
  • the MWAP output could be looped back to the input to compute multiple sets of n without host intervention, as shown in FIG. 10.
  • the linear array could be programmed so that data and calculations flow first to the right through the array and then flow back to the left allowing additional sets to be computed; and, then flow again reverses and data and calculations flow to the right were the answers are retrieved by the host computer from the right most dual-post memory element. Changing the direction of flow is accomplished merely by programming a change in the base registers. This feature, allowing both right and left flow of data and calculations is not taught by the prior art processing arrays.
  • the throughput rate of the MWAP could be increased by using multiple sets of three processing element/linking memory pairs to compute more than one point, n, at the same time. This extension is illustrated in FIG. 11. Note that the loop back scheme shown in FIG. 10 could be used in the FIG. 11 configuration to compute multiple points before returning data to the host. These examples illustrate three additional properties of the MWAP:
  • the asynchonous dual-port memory linking elements permit simple extension of the MWAP processor to any length (size). Since there is no global clock controlling each PE propagation delays will not limit the size of the processing array.
  • MWAP can be loaded into the same MWAP for execution, or the MWAP can contain several different algorithms in its program memory at the same time allowing one to change the function computed by simply changing the starting address in the PE program cache. If a linear array of processor elements contain more elements than required for a given algorithm, the results can simply be propagated to the last dual-port memory linking element without change.
  • More than one computation (function) can be applied to the input before the data is returned to the host. That is, algorithms can be cascaded in the MWAP.
  • the instruction sequence stored in the program cache of each PE determines the calculation functions provided by the PE.
  • each processing element can be programmed to compute the next value of its coefficient as data flows through the array.
  • This extension permits the MWAP to handle partial differential equations with variable coefficients. However, the throughput rate of the processor will decrease by the time required to compute the new value of a coefficient.
  • a more elegant solution is to use a two dimensional MWAP array as shown in FIG. 12. In this configuration, the first row of processor/linking memory elements 146 executes the algorithm for computation of the heat conduction equation. The second row of processor elements 148 computes the next value of the coefficients, to be used by the first row of processor elements.
  • the coefficient values are stored in the columns of dual-port memory linking elements (150, 152, 154) for use by the top row of processors as needed.
  • the throughput rate for the MWAP is increased as the computation of new coefficients is done in parallel with the computation of the heat conduction equation.
  • the MWAP can compute two-dimensional array problems using a linear array of processor/memory elements.
  • processor/memory elements To illustrate the importance of this property of the Memory-Linked Wavefront Array consider the broadcast, systolic, and wavefront array algorithms for multiplication of two non-sparse matrices:
  • This approach can be used for Matrix Multiplication by broadcasting the columns of A and rows of B instantly along a square array; with the inner-products then sequentially summed via a program loop in each processor.
  • This type of prior art implementation is shown in FIG. 13.
  • the product C can also be computed using the inner product accumulation:
  • One prior art implementation for matrix mutliplication using inner product accumulation is the systolic array shown in prior art FIG. 14.
  • A is propagated into the left edge of the processors
  • B is propagated into the top edge of processors
  • C (initially 0) is prorated diagonally through the array from the upper left corner.
  • Global clocking of the array, used in the systolic array requires each processing element to process data at each clock pulse.
  • the different columns of B and rows of A have to be adjusted by the extra zeros shown, in order to arrive at each processing element at the correct time.
  • As each set of A's arrive at a processor element they are multiplied and added to the current partial sum in the processing element. The result is propagated out of the array on the bottom diagonal.
  • the wavefront array processor uses the concept of a computation wavefront traveling down the processor array. Each processor modifies a term in the wavefront and acts as a secondary source responsible for the propagation of the wavefront.
  • a wavefront in the processing array corresponds to a mathematical recursion in the algorithm. Successive pipelining of the wavefronts computes all recursions in the algorithm.
  • FIG. 15 A prior art Wavefront Array processor for matrix multiplication is shown in prior art FIG. 15. Note that memory 156, 158 in the prior art array is placed on the top and left sides of the array of processor. To implement matrix multiplication on this type of array, the registers of all the processing elements are initially set to zero:
  • FIGS. 16 and 17 illustrate that this matrix multiplication problem which is so difficult and cumbersome to handle on the systolic array or the prior art wavefront array can be simply handled on the MWAP architecture.
  • the prior art wavefront array processor requires a two-dimensional processing array
  • the problem can be handled by MWAP in a simple linear array.
  • FIG. 16 illustrates that the multiplication can be accomplished in a three-processor linear array by storing data and coefficient in the dual port memory (PPM) between processing stages. Interleaved columns of the matrix B and rows of the matrix A shown are entered in reverse order from the bottom to the top of the matrix. The rows of matrix A are entered in reverse order from right to left.
  • Each processing element computes one term of the partial sum for each output term C(ij) as they are prorated through the array.
  • the computation sequence is outlined in FIG. 17.
  • Each processor element in the MWAP essentially does the computations of a vertical row of processors in the systolic or prior art wavefront implementation. This is made possible by holding coefficient in the dual-port memory linking elements between the processing elements.
  • the first fourteen cycles shown in FIG. 17 are initialing the array by loading coefficients for the multiplication. The time to do this corresponds to the time required to load coefficients into the memories along the edge of a prior art wavefront array.
  • the computation time for each row of the output matrix is 2N+1 processor cycles, where N is the size of the square matrix.
  • the total computation time for the multiplication of two square matrices of size N is N(2N+1) processor cycles.
  • the computation time for N processors to compute an N X N product is approximately proportional to N squared. That this is approximately the same, or slightly better than, the performance obtained with a systolic or prior art wavefront array can be seen as follows: Assume one has nine processors to use in computing a 9 ⁇ 9 full matrix multiplication. If a linear MWAP array is used, it will require approximately 9(2*9+1) or 171 processor cycles.
  • A(ij), B(ij), and C(i,j) are all 3 ⁇ 3 matrices.
  • N x N systolic or prior art wavefront array can compute a N x N matrix product in approximately N processor iterations, the computation of each C(ij) term will require 3*N or 9 processor iterations. Thus computation of the entire C matrix for prior art arrays will require 9 ⁇ 9 or 81 processor iterations plus the time required to perform 18 matrix additions.
  • the basic iteration for matrix multiplication with a prior art wavefront array is:
  • the simultaneous computation and multidirectional communication capability of the MWAP yields a significant increase in its throughput rate. In fact, for most algorithms the MWAP will be faster than either a systolic or prior art wavefront array.
  • linking memory permits a single linear MWAP array to implement a board variety of both 1-D and 2-D geometry algorithms.
  • the Fourier transform recursion formula is as follows: ##EQU6## with p, q and r varying from stage to stage.
  • This Fast Fourier Transform, (FFT) calculation requires only N*log 2 (N) operations to compute a transform of size N.
  • N log 2
  • the recursion formula is faster than direct computation using the discrete Fourier transform.
  • FIG. 18 which is a signal flow graph for the decimation-in-time constant-geometry FFT algorithm. This variation in the distance between input data points, or global communication requirement, makes it impossible to implement the FFT using the recursion formula on a systolic or prior art wavefront array.
  • One method using the MWAP for implementing the FFT using the recursion formula would be to use a processing element for each term in the algorithm with the processors interconnected as shown in FIG. 18. This would require N processors for a N point transform.
  • the same linear array Memory-Linked Wavefront Array Processor used in the previous examples can compute the Fast Fourier Transform.
  • the input is stored in the first dual-port memory linking element in bit-reversed order
  • the W coefficients are stored in the dual-port memories linking elements between stages in bit-reversed order
  • the sum and difference terms are propagated between processors using two base address registers. This makes the addressing of coefficients and data between stages linear, as can be seen in FIG. 19.
  • the MWAP computes the FFT as follows:
  • Each stage of the FFT is implemented using one MWAP processing module which computes X(p)+W(r)*X(q) and X(p)-W*(r)X(q).
  • the processor at each stage alternates between using memory address register A and memory address register B to output
  • the processor at each stage reads computation points from the dual-port memory linking elements to its left alternately using memory address base resistor A and B.
  • the algorithm is illustrated in FIG. 19 with time snapshots of the computation of a 16-point FFT.
  • the MWAP implements the FFT using 1n(N) processors for a size N transform and performs multiple Fourier Transforms, of length N, in N/2 systolic cycles.
  • the MWAP architecture that can implement algorithms that are not possible with systolic or prior art wavefront arrays.

Abstract

A Memory-Linked Wavefront Array Processor (MWAP) is disclosed which computes a broad range of signal processing, scientific and engineering problems at ultra-high speed. The memory-linked wavefront array processor is an array of identical programmable processing elements linked together by dual-port memory elements that contain a set of special purpose control flags. All communication in the network is done asynchronously via the linking memory elements, thus providing asynchronous global communication with the processing array. The architecture allows coefficients, intermediate calculations and data used in computations to be stored in the linking elements between processing stages. The novel architecture also allows coefficients, intermediate calculations and data to be passed between the processing elements in any desired order not restricted by the order data is to be used by the receiving processing element. Further, each processing element is capable of simultaneous arithmetic computation, multi-direction communication, logic discussions, and program control modifications.

Description

STATEMENT OF GOVERNMENTAL INTEREST
The Government has rights in this invention, pursuant to Contract No. N000024-85-C-5301, awarded by the Department of the Navy.
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to an array processor having a unique architecture for computing a broad range of signal processing, scientific, and engineering problems at ultra-high speed. More particularly, the invention called a Memory-Linked Wavefront Array Processor (MWAP) comprises a computing architecture that provides global asynchronous communication within the processing array and also provides local/data driven asynchronous control of each processing element.
2. Description of the Prior Art
Signal processing today requires high computation rates. In many cases the signal processing algorithm is straightforward, but the data rate and subsequent processing overwhelms existing computers and as a result, one is forced to limited application situations and/or long computation times. In the field of engineering there is also a need for improved computer speed and reduced cost. System simulations in the areas of hydrodynamics, aerodynamics, electromagnetics, chemistry and heat transfer are usually limited by computer speed, memory and cost. As a result, full simulations of basic phenomena are frequently not feasible in engineering design. The problem is twofold, first to increase system computation speed by one or two orders of magnitude, and second to design a system applicable to a multiplicity of problems.
The systolic array, introduced by H. T. Kung (see, H.T. Kung, "Let's Design Algorithms for VLSI Systems", in Prac. Caltech Conf. VLSI, Jan. 1979, pp. 66-90), is an array of processors that are locally connected and operate synchronously on the same global clock. Algorithms are executed in a pulsed (systolic flow) fashion. That is, the network of processors rhythmically compute and pass data through the system.
The systolic array has the properties of modularity, regularity, local interconnection, and highly pipelined, highly synchronized multiprocessing. However, it requires global synchronization. That is, data movement is controlled by a global timing-reference. In order to synchronize the activities in a systolic array, extra delays are often used to ensure correct timing. For large arrays of processors, synchronization of the entire computing network becomes intolerable or even impossible.
In its classic form, examples of which are shown in FIG. 1, the systolic array is not programmable; each algorithm requires a separate and distinct array configuration. With increased complexity, the systolic array can be made "hardware programmable" by using matrix switches to reconfigure the array geometry. In any case, the systolic array always requires a direct mapping of the computation algorithm onto physical processor elements.
A second attempted solution, the wavefront array processor uses the same geometric structures as the systolic array and is generally described in: S.Y. Kung et al, "Wavefront Array Processor: Architecture, Language and Applications", MIT Conf. on Advanced Research in VLSI, Jan. 1982, MIT, Cambridge, MA. It differs from the systolic array in that control flows through the array along with data and parameters. This addition of local control flow to local data-flow permits data-driven, self-timed processing. Conceptually, the requirement of correct "timing" is replaced by the requirement for correct "sequencing".
Every processor element (PE) in a wavefront array processor has a bidirectional buffer with independent status flags for each adjacent PE. The flow of data is asynchronous between PE's with control tokens sent between PE's to determine data availability and data use. This relaxes the strict timing requirement of the systolic array, simplifies algorithm development, and often results in faster algorithms and processing speed. The wavefront processor thus operates by passing control and data between processors in a wavelike fashion so that computation flows from one processor to the next as each processor completes a recursion (step) in the algorithm.
However, both the systolic and wavefront array processors are deficient in that they require local-type communication and can't handle global-type communication. As a result, certain useful algorithms can't be calculated using prior art systolic and wavefront array processors. For example, Fast Fourier Transform, FFT, is calculated using the following recursion formula (the decimation-in-time constant geometry FFT algorithm):
x(m+1,p)=x(m,p)+W(k,N)*x(m,q)
x(m+1,q)=x(m,p)-W(k,N)*x(m,q)
with p and q varying from stage to stage. Calculation of this algorithm requires global-communication since the distance |p-q| between data points increases from stage to stage. But, systolic and prior art wavefront array processors require the distance between data items to remain constant from processor (stage) to processor. Thus a systolic or wavefront array processor could not be used to calculate FFT using the above recursion formula.
Similarly, the computing capability and flexibility of the prior art array processors is limited because of the requirement that data must pass between the processing elements in the order in which that data is to be used by the receiving processing element. This deficiency in the prior art makes the calculation of certain algorithms difficult and cumbersome.
SUMMARY OF THE INVENTION
The present invention, called a Memory-Linked Wavefront Array Processor (MWAP), extends the wavefront array processor to handle global-type communication. By inserting "smart memory" containing control flags between the processor elements, the memory-linked wavefront array processor relaxes the requirement for strict local communication dictated by the prior art, and therefore permits implementation of the FFT algorithm using the recursion formula. This invention also enlarges the computation power and flexibility of array processors by relaxing the prior art requirement of passing data between the processing elements in the order in which that data is to be used by the receiving processing element.
The MWAP utilizes a new array processing architecture which can compute a broad range of signal processing, scientific, and engineering problems at ultra-high speed. In its most generalized form, the invented MWAP architecture comprises an array of identical programmable processing elements linked together by dual-port memory linking elements that contain a set of special purpose control flags. All communication in the network is done asynchronously via these linking memory elements. Data driven/local control is obtained by using asynchronous handshaking between the processing elements and the dual-port memory linking elements. Moving the asynchronous link to the dual-port memory linking elements permits the use of sequence control "tokens" to be replaced by hardware control flags in each memory linking element. Each processing element is capable of simultaneous arithmetic computation, communication in two directions, logic decisions, and program control modification.
The MWAP has the properties of modularity, regularity, local interconnection, and highly pipelined multiprocessing. Later in this Specification, computation of algorithms using the MWAP architecture are compared to those used for typical prior art systolic and wavefront array processors to illustrate some of the unique capabilities and properties of the MWAP architecture. In general, the MWAP is shown to provide higher throughput rates for most algorithms, to extend the range of algorithms that can be implemented on array processors, and to permit a single linear array configuration to be programmed for a wide variety of algorithms that could previously only be handled on more complex two dimensional prior art systolic and wavefront arrays.
The following is a partial list of novel features found in the present invention:
A first novel feature of the invention is to provide global asynchronous communication within an array of processing elements by linking together adjacent processing elements via asynchronous dual-port memory linking elements.
A second novel feature of the invention is that data can be passed between processing elements in any desired order not restricted by the order that data is to be used by the receiving processing element.
A third novel feature of the invention is that coefficients and other information or data used in calculating an algorithm can be stored in the dual-port memory linking elements between processing stages in an array processor.
A fourth novel feature of the invention is that data-driven/local control of each processing elements is obtained using asynchronous handshaking between each processing element and the dual-port memory linking element located adjacent in the array.
A fifth novel feature of the invention is that moving the asynchronous link to the memory linking elements, permits software sequence control "tokens" to be replaced by hardware control flags located in the memory linking elements.
A sixth novel feature of the invention is that the processing operation of a particular processing element is suspended when it attempts to access a memory location in the adjacent dual-port memory linking element until such time as a control flag associated with such memory location has been set by another processing element adjacent to the particular dual-port memory linking element.
A seventh novel feature of the invention is that each particular processing element has an internal control and bus arrangement which permits simultaneous communication with its adjacent dual-port memory linking elements in the processing array.
An eight novel feature of the present invention is that each processing element can multiply, add or subtract, read or write to its left adjacent memory linking element and read or write to its right adjacent memory linking element, in a linear array, all during the same instruction cycle.
A ninth novel feature of the present invention is that data and computation can be propagated to the right or left in a linear array or to the right or left or up or down in a two dimensional array.
A tenth novel feature of the present invention is that each processing element in the MWAP can store several different program sequences for computing different algorithms, so that different processing elements in an array can perform different computations or the same processing element can perform different computations at different times during the computation cycles.
BRIEF DESCRIPTION OF THE DRAWINGS
In order that the present invention may be more fully understood, it will now be described, by way of example, with reference to the accompanying drawings in which:
FIG. 1 illustrates the general architecture of prior art array processors, FIG. 1A illustrating a linear array and FIG. 1B illustrating a 3×3 square array;
FIG. 2 is a block diagram illustrating a linear array Memory-Linked Wavefront Array Processor, as taught by the present invention;
FIG. 3 is a block diagram illustrating a two-dimensional geometric array structure for the Memory-Linked Wavefront Array Processor, as taught by the present invention;
FIG. 4 is a block diagram of a processing element used in a linear MWAP array;
FIG. 5 is a block diagram of a processing element used in a two-dimensional MWAP array;
FIG. 6 is a detailed block diagram illustrating the internal register and bus arrangement for a typical processing element in the MWAP;
FIG. 7 is the sequencer block diagram for a typical MWAP processing element;
FIG. 8 is a block diagram showing the internal structure of a dual-port memory linking element used in the MWAP architecture;
FIG. 9 is a flow diagram illustrating the FIR filter processing sequence for a MWAP;
FIG. 10 illustrates the use of a MWAP data loop back to calculate multiple points in the 1-D heat conduction equation;
FIG. 11 illustrates the use of a MWAP for simultaneous computation of multiple points in the 1-D heat conduction equation;
FIG. 12 illustrates the use of a two dimensional MWAP to compute partial differential equations with variable coefficients;
FIG. 13 illustrates the use of a prior art broadcast array for full-matrix multiplication;
FIG. 14 illustrates the use of a prior art hex-connected systolic array to compute matrix multiplication;
FIG. 15 illustrates the use of a prior art wavefront array to compute matrix multiplication;
FIG. 16 illustrates the use of a linear MWAP array to compute matrix multiplication as taught by the present invention;
FIG. 17 is a flow diagram illustrating the computation sequence for a 3×3 matrix multiplication using the linear MWAP array shown in FIG. 16;
FIG. 18 illustrates the shuffle-exchange needed to compute the Fourier Transform using the recursion formula; and,
FIG. 19 illustrates the computation sequence used by a MWAP to compute the Fourier Transform using the recursion formula.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
The MWAP uses a modular structure for both the processing hardware and for programming the system. The system architecture can be implemented with a linear processing array, a two-dimensional processing array, or an n-dimensional processing array, where n is an integer (NOTE: because the MWAP does not require a global clock like the systolic array processor, propagation delays won't limit the size of the array.) The basic linear MWAP array architecture, shown in FIG. 1, consists of a host interface 10 operably connected to a dual port memory linking element 12, multiple processing element/dual port memory linking element pairs 14, and a host output interface 16. The dual port memory linking element may be composed of memory chips or a set of registers.
Asynchronous local communication is provided between each processing element and its adjacent dual port memory linking elements. Data, coefficients used in calculations, intermediate calculations and/or other information can be stored in selected memory locations in each dual port memory linking element. Asynchronous communication between processing elements occurs, for example, as data and other information is written into a memory location in dual port memory linking element 22, by one processing element 20, and is acquired, after appropriate handshaking, by another adjacent processing element 24. In this example, processing element 20 is not required to write data into the dual port memory linking element 22 in the same order that data is used by the receiving processing element 24. In fact, processing element 24 may pass through data or information from the adjacent dual port memory element 22 to adjacent dual port memory 26 without processing the data or information, and allowing a downstream processing element to acquire that data or other information for its processing purposes. (The prior art array processing architecture is shown in FIG. 1, contains an array of processing elements 28 which are directly interconnected. Memory blocks 30 are located external to the processing array and along its edges. As will be shown later in the Specification, many algorithm computations are difficult and cumbersome with the prior architecture.) In the MWAP architecture, each processing element may access memory locations in a right adjacent dual port memory element and a left adjacent dual port element. Therefore, the asynchronous local communication provided via the dual port memory linking elements makes available global communication within the processing array.
As will be discussed in greater detail by specific example, linking the processing elements with dual port memory linking elements provides the following advantages: (1) global communications; (2) data and computation can be propagated to the right or left; (3) the distance between data elements can increase or decrease between processing stages; (4) coefficients and other information can be stored between processing stages during an initialization phase; and, (5) both single and two-dimensional algorithms can be processed using a linear array.
Since the asynchronous link occurs between the processing element and the dual port memory linking element, a hardware control flag located in the dual port memory element can replace a software control token. This feature, which shall be described later, allows data driven/local control to be obtained using asynchronous hardware handshaking between a processing element and its adjacent dual port memory linking elements. Once the processor array is initialized, data and information is rhythmically read from one dual port memory element and output flows to a down stream dual port memory with each processing element self-timed by the availability of data in its adjacent dual port memory elements.
FIG. 3 is a block diagram illustration of the basic MWAP architecture for a two-dimensional processing array. As with the linear array, dual port memory linking elements 32 are interspersed between processing elements 34 in the array. A processing element 34 may have direct access to adjacent dual port memory linking elements to its right and left as well as up and down in the array. Processing element 32 and dual port memory linking element 34 in the two-dimensional array, operate similar to those elements in the linear array. The basic MWAP architecture can be extended by application of this invention to any n-dimensional array. It is further within the scope of the present invention to use n-port memory linking elements and n-port processing elements, where n is greater than two.
FIG. 4 is a block diagram illustrating one embodiment of the modular processing element, as taught by the present invention for use in a linear MWAP array. The processing element can be separated into three sections: the arithmetic section ( elements 36, 38, 40), the addressing registers (elements 42, 44), and the program flow control block (or control logic, elements 46, 48). The arithmetic section consists of two arithmetic processors (36, 40), internal arithmetic registers 38, and associated data bus structure. The address registers consist of a group of eight counter/register pairs (42, 44) for each memory port the processing element can access. FIG. 4 shows two groups of address registers so that each processing element can access dual-port memory linking elements to its right and left (see FIG. 2). Address registers 42 are used to address memory locations in the right adjacent dual-port memory linking element; and address registers 44 are used to address memory locations in the left adjacent dual-port memory linking element. The control logic section contains a program memory 46 and associated logic 48 to make the processing element programmable.
Control unit 48 senses and either sets or resets hardware control flags in the right adjacent dual port memory linking element via line 50, and in the left adjacent dual port memory linking element via line 52. Control unit 48 will suspend operation of the processing element when the program sequence calls for one of the address registers (42, 44) to access its adjacent dual port memory element and a control flag in that dual port memory element associated with that memory field (or associated with that particular address register) remains down. The control unit will continue to suspend activity of the processing element until that particular flag in the adjacent dual port memory linking element has been set by the other processing element adjacent to the particular dual port memory linking element. In this way, the processing unit is self-timing and will remain inactive until the required data is available. Thus, each processing element will have asynchronous data driven local control. Since the processing element suspends operation during those periods when a control flag indicates unavailability of data, there is no chance for the contamination of data by two processing elements attempting to read and write into the same memory location simultaneously. Each control flag in the dual port memory linking elements have two states, and the control unit in the adjacent processing elements are programmed so that when a flag is in a particular state it will appear to be a set flag to one of the adjacent processing elements and a reset flag to the other adjacent processing element.
Further, the invented architecture may use two or more registers to access different data locations in a particular adjacent dual port memory linking element. Since each dual port memory element may have two or more control flags (each control flag associated with an address register in said adjacent dual port memory element), memory overlapping is possible. In other words, a processing element to the right of a particular dual port memory linking element may read or write data using one of its address registers from a first location in a particular dual port memory element and a processing element to the left of that particular dual port memory element may simultaneously read or write data into a second memory location in that dual port memory element. In this example, flag 1 (located in the dual port memory element and associated with the first memory location), would appear set to the right processing element and re-set for the left processing element; and, flag 2 (also located in the dual port memory) will be reset for the right processing element and set for the left processing element.
It will also be noted from the bus structure in FIG. 4, that the processing element can read or write from the left dual port memory from bus 62, while simultaneously reading or writing from the right dual port memory means from bus 60. This is possible because the internal bus arrangement (64, 66) provides separate access to the input registers 54 and the output registers 58 from either said right port 60 or said left port 62. Further, instruction words stored in the program memory 46 have separate fields to control read/write operations from the right port 60 and said left port 62. Thus, a read or write to the left port and a read or write to the right port may all occur in the same instruction cycle. Similarly, bus arrangement (64, 66) as well as the use of internal registers 38 separating the multiplier/divider 36 from the adder/subtractor 40, allow simultaneous multiplication/division and addition/subtraction to occur. Again, the instruction words stored in program memory 46 have separate fields to control the multiplier, adder, and left and right data port addresses. Since these operations can occur in parallel, a multiply, add or subtract, or a read or write to the left port, and a read or write to the right port may all occur in the same instruction cycle.
FIG. 5 is a block diagram illustrating one embodiment of a processing element for use in a two-dimensional processing array. The basic processing element used in the linear array (see FIG. 4) is similar to that used for a two-dimensional array; except that processing element 67 has four separate sets of address registers (42, 44, 68 and 70) to access adjacent dual port memory lining elements located to the right, left, and up and down in the two dimensional array from the processing element. Similarly, four control lines 72 sense and set or reset hardware control flags in the adjacent right, left, up and down dual port memory linking elements. As described above, overlapping of memory using two or more control flags in each dual-port memory linking element, and the simultaneous read or write to the left, right, up and down dual port memory elements, as well as simultaneous add/subtraction and multiplication are all features also obtained in the MWAP two-dimensional array.
FIG. 6 represents a more detailed block diagram of the modular processing element as taught by the present invention. In order to reduce the complexity of the following discussions, FIG. 6 shows a processing element used in a linear array. However, it is to be understood that it is within the scope of this invention to extend the particular structure shown in FIG. 6 to any multi-dimensional array.
The processing element consists of: a control unit 74 having an instructional cache and program sequencer; a block of memory address registers 76 to address adjacent dual port memory linking elements (not shown) along right address bus 78 and left address bus 80; a floating point multiplier 82; a floating point arithmetic section (ALU) 84; input registers 86; output registers 88; and, internal arithmetic registers 90. The output registers 88, input registers 86, and internal arithmetic registers 90 are each separately connected to right output bus 92, right input bus 94, left output bus 96 and left input bus 98. Input/output buses (92, 94) are operably coupled to the right dual port memory linking element and input/output buses (96, 98) are operably coupled to the left dual port memory linking element. Once the instructional cache, located in control unit 74, is loaded, program and data memory are separate. All memory addressing is done by reference to the memory address registers 76 which can read, or read and then incremented, or read and then reset to a base address assigned during the program load. The processing element can simultaneously read or write to memory locations in the adjacent right dual port memory linking element and the adjacent left dual port memory linking element. Control lines 108 and 110 enabled the control unit 74 to sense and set, or reset, hardware control flags located in the adjacent left or adjacent right dual port memory linking element. As discussed earlier, the control unit 74 will suspend the processing operation of the particular processing element when a program instruction calls for address register 76 to access a memory location in an adjacent dual port memory element and an associated control flag in said adjacent dual port memory element has not as yet been set.
The arithmetic section consists of fourteen arithmetic registers (label R0 through R13 in FIG. 6), a floating point multiplier 82 and, a floating point adder/subtracter 84. The registers 90 are connected using a specialized bus structure designed to support multiply and accumulation algorithms. Only two registers (R0 and R13) are connected to both the left and right input buses (94, 98) and both output buses (92, 96). Six registers are attached to input buses only (R1, R2, R4, R6, R9 and R11), and four are available to output buses only (R7, R8, R12 and R13). Two registers, R5 and R10, are not connected to any input or output bus. This structure supports efficient real and complex number operations with a minimal number of registers and interconnects.
The multiplier, adder/subtracter, left and right data ports are independently controlled by separate fields in the processing element instruction words. Since the separate instruction fields allow these operations to occur in parallel, a multiply, an addition or subtraction, and read/write by to the left port, or read/write to the right port, may all occur in the same instruction cycle.
The addressing section consists of two groups (100, 102) of eight counter/register pairs. One group 102 serves as the left address counters (LAC0 to LAC7) and the other group 100 serves as the right address counters (RAC0 to RAC7). Associated with each address counter is a base register 104. This base register is used to hold a reference memory address for the counters. During each instruction that memory is referenced, a counter 106 that supplied the address can be incremented, or reset to the value in its base address register, or the counter can remain unchanged. To facilitate the generation of addresses when performing the fast fourier transform and similar algorithms, the outputs of address counters LAC6, LAC7, RAC6 and RAC7, are placed on the address bus in bit reverse order. The transform size associated with this bit reversal is programmable.
An expanded block diagram of the programming sequence section 74 is shown in FIG. 7. It contains a program memory 112, a program address counter 114, and four program branch address registers 116. In addition, there are two looping counters 118, 120 (LOOP 1 and LOOP 2) that are used for conditioning branching out of the loops. The base register (122, 124) are attached to each counter for resetting the loop count. One counter can be modified during each instruction cycle. It can be either incremented, decremented or reloaded from its base register. In addition to these loop counters, arithmetic register 112 (see FIG. 6) can be used for conditional branching. This allows conditioning branching that is data dependent.
FIG. 8 is a block diagrammatic view of the dual port memory linking element as taught by the present invention. The dual port memory linking element has two unique features: (1) it is asynchronously driven at its boundary, and (2) it contains two flags 126. Data flow in the MWAP is controlled by these flags. These flags are used to indicate the availability of data to an adjacent processing element. Any instruction that uses LAC0 or RAC0 (see FIG. 6) in the processing element as the address for memory access is not executed unless control flag 1 in the associated dual port memory linking element is set. If an instruction of this type attempts execution when flag 1 is not set, the instruction execution halts until access is permitted by the setting by the control flag. When the flag is set, the instruction execution begins. In a similar way, flag 2 controls the execution of instructions referencing LAC 1 and RAC 1 (see FIG. 6). If the dual port memory linking element depicted in FIG. 8 were located in the array to the left of the processing element depicted in FIG. 6, the address register 142 on the right port of the dual-port memory linking element would connect to bus 76, the input data fifo 140 and output data fifo 138 would respectively be connected to buses 98 and 96 and the right port handshake logic 136 would connect to control lines 108. Similarly, address register 134, input data fifo 132, output data fifo 130 and handshaking logic 128 associated with the left port of the dual port memory linking element would connect to similar elements in a processing element located to its left. Static RAM memory 136 can therefore be accessed by the processing element to its adjacent left and its adjacent right. As discussed previously, with the use of two control flags, the adjacent processing elements can have overlapping access to different portions of static RAM 136. This would enable to left adjacent processing element and the right adjacent processing element simultaneous access to different portions of static RAM 136.
Operation of the Memory-Linked Wavefront Array Processor (MWAP) and some of its properties are illustrated with the following implementation of a Finite Input Response (FIR) Filter for signal processing. The equation for a FIR filter is: ##EQU1## Writing out the first few terms for a two state filter, i.e., N=2 we have:
______________________________________                                    
         PE#3                                                             
Y(0) =   b(0) × (0)                                                 
                    PE#2                                                  
Y(1) =   b(0) × (1) +                                               
                    b(1) × (0)                                      
                               PE#1                                       
Y(2) =   b(0) × (2) +                                               
                    b(1) × (1) +                                    
                               b(2) × (0)                           
Y(3) =   b(0) × (3) +                                               
                    b(1) × (2) +                                    
                               b(2) × (1)                           
Y(4) =   b(0) × (4) +                                               
                    b(1) × (3) +                                    
                               b(2) × (2)                           
______________________________________                                    
Once all of the filter coefficients, b(n), are read into the processing elements each Processing Element (PE) in the MWAP computes one term of the wavefront b(k)x(i), and forwards the input x(i) and partial sum to the next PE. The first PE reads the input data stream and the last PE sends the output Y(i) to the host computer or system bus. The FIR algorithm is calculated using the linear array shown in FIG. 9; and the sequence of events is also illustrated for several processing cycles in FIG. 9. Cycles 1 and 2 essentially inialize the array. (The notation > indicates the direction data is being read or written, for example, in cycle 1, data x(0) is being read from DPM #1 and in cycle #2 data x(2) is being written into DPM2). In cycles 3 through 5 processing element #1 reads x(1) from the memory to its left, computes the b(2)x(1) term, and writes both x(1) and the previous product b(2)x(0) into the memory to its right, using the base address specified by memory address register #1. As PE #1 completes storing the partial sum and x(1) in the memory to its right, it sets control flag #1 in that memory to notify PE #2 that data is ready for it to process. (Note:the notation #1 and #2 connected to an arrow indicates the setting and resetting of Flag 1 and 2, respectively.) PE #1 then repeats the process for x(2) using memory address register #2 and control flag #2. This sequence is repeated using first address register #1 and control flag #1 and then address register #2 and control flag #2 to process all input samples x in the left memory. If the host is continuously entering new data samples into the left most memory, the MWAP can continuously filter the input data forever.
When the control flag #1 is set, processing element #2 reads x(n) and the partial sum from the memory to its left. It then resets control flag #1, to permit PE #1 to use that section of the memory again, and adds the product b(1)x(n+1) term to the partial sum to obtain the new partial sum b(2)x(n)+b(1)x(n+1). The data sample x(n) and the previous partial sum is written into the memory to its right, using the base address specified by its memory address register #1. As PE #2 completes storing the partial sum and x(n) in the memory to its right, it sets the control flag #1 in that memory to notify PE #3 that data is ready for it to process. PE #2 then repeats the process for x(n+1) using its memory address register #2 and control flag #2 in the memory to its left; setting control flag #2 in the memory to its right. The sequence is repeated over and over just as with the first processing element.
Processing element #3 reads the partial sum and x from the memory to its left, adds the product b(0)x(n+2) to the partial sum and puts the answer in the memory to its right using the same sequence of memory address registers and control flags as described for processing elements #1 and #2. Thus, the results Y(0), Y(1), . . . are written into the right-most dual port memory for reading by the host computer.
The FIR processing sequence illustrates several properties of the Memory-Linked Wavefront Array Processor:
1. Computations flow through the MWAP. Once inialized, input data is rhythmically read from the left memory linking element with results output to the right memory linking element. In the example processing sequence, data is input, processed, and output every two process cycles.
2. The MWAP is self-timing (there is no need for a global clock controlling the individual PEs), i.e., the flow of computations is controlled by the two flags in each dual port memory. Note that the use of two control flags permits overlapping of data buffers (e.g., the PE to the right and left of a dual-port memory linking element can simultaneously access different memory locations in that dual-port memory linking element). In fact, two control flags generally permit efficient processing of any MWAP algorithm.
3. The MWAP throughput rate depends only on the number of processing elements/linking memory pairs used and the algorithm implemented; not on the size of the data set processed or the length of the computation. For example, the MWAP throughput rate does not change for longer (more stages) FIR filters if one additional PE/Memory linking pair is used for each additional stage in the filter.
Not only can a broad class of one-dimension algorithms be easily implemented on the MWAP; the MWAP is easily extended to increase its throughput rate. This can be illustrated with the following solution of the 1-D heat conduction equation: ##EQU2## Using the FIR structure discussed above: Let:
b(0)=a
b(1)=b
b(2)=c
and
x(i)=T(i) for a given n
Then:
______________________________________                                    
           PE#3                                                           
T.sup.n+1 (*) =                                                           
           aT.sup.n (0)                                                   
                    PE#2     (initialization step)                        
T.sup.n+1 (0) =                                                           
           aT.sup.n (1) +                                                 
                    bT.sup.n (0)                                          
                             PE#1                                         
T.sup.n+1 (1) =                                                           
           aT.sup.n (2) +                                                 
                    bT.sup.n (1) +                                        
                             cT.sup.n (0)                                 
T.sup.n+1 (2) =                                                           
           aT.sup.n (3) +                                                 
                    bT.sup.n (2) +                                        
                             cT.sup.n (1)                                 
T.sup.n+1 (3) =                                                           
           aT.sup.n (4) +                                                 
                    bT.sup.n (3) +                                        
                             cT.sup.n (2)                                 
______________________________________                                    
With these substitutions, the same algorithm used for the FIR filter on the MWAP can be used to solve a single point, n, in the 1-D heat equation with each interaction of the MWAP. In addition, the MWAP output could be looped back to the input to compute multiple sets of n without host intervention, as shown in FIG. 10. As an alternative arrangement, rather than having the data loop back along bus 144 the linear array could be programmed so that data and calculations flow first to the right through the array and then flow back to the left allowing additional sets to be computed; and, then flow again reverses and data and calculations flow to the right were the answers are retrieved by the host computer from the right most dual-post memory element. Changing the direction of flow is accomplished merely by programming a change in the base registers. This feature, allowing both right and left flow of data and calculations is not taught by the prior art processing arrays.
The throughput rate of the MWAP could be increased by using multiple sets of three processing element/linking memory pairs to compute more than one point, n, at the same time. This extension is illustrated in FIG. 11. Note that the loop back scheme shown in FIG. 10 could be used in the FIG. 11 configuration to compute multiple points before returning data to the host. These examples illustrate three additional properties of the MWAP:
4. The asynchonous dual-port memory linking elements permit simple extension of the MWAP processor to any length (size). Since there is no global clock controlling each PE propagation delays will not limit the size of the processing array.
5. Different algorithms can be loaded into the same MWAP for execution, or the MWAP can can contain several different algorithms in its program memory at the same time allowing one to change the function computed by simply changing the starting address in the PE program cache. If a linear array of processor elements contain more elements than required for a given algorithm, the results can simply be propagated to the last dual-port memory linking element without change.
6. More than one computation (function) can be applied to the input before the data is returned to the host. That is, algorithms can be cascaded in the MWAP. The instruction sequence stored in the program cache of each PE determines the calculation functions provided by the PE.
If the coefficients a, b and c, in the heat conduction equation are not constant, each processing element can be programmed to compute the next value of its coefficient as data flows through the array. This extension permits the MWAP to handle partial differential equations with variable coefficients. However, the throughput rate of the processor will decrease by the time required to compute the new value of a coefficient. A more elegant solution is to use a two dimensional MWAP array as shown in FIG. 12. In this configuration, the first row of processor/linking memory elements 146 executes the algorithm for computation of the heat conduction equation. The second row of processor elements 148 computes the next value of the coefficients, to be used by the first row of processor elements. The coefficient values are stored in the columns of dual-port memory linking elements (150, 152, 154) for use by the top row of processors as needed. Thus, the throughput rate for the MWAP is increased as the computation of new coefficients is done in parallel with the computation of the heat conduction equation.
MWAP CONFIGURATION PROPERTIES
The MWAP can compute two-dimensional array problems using a linear array of processor/memory elements. To illustrate the importance of this property of the Memory-Linked Wavefront Array consider the broadcast, systolic, and wavefront array algorithms for multiplication of two non-sparse matrices:
C=A*B
where:
A=[A(i,j)] and B=[B(i,j)]
The calculations below show the multiplication process for a 3×3 matrix: ##EQU3##
If matrix A is decomposed into columns A{x} and matrix B is decomposed into rows B{y}, then the product of A and B can be computed by:
C=A{1}*B{1}+A{2}*B{2}+. . . +A{N}*B{N}                     [1]
This approach can be used for Matrix Multiplication by broadcasting the columns of A and rows of B instantly along a square array; with the inner-products then sequentially summed via a program loop in each processor. This type of prior art implementation is shown in FIG. 13.
In the broadcast array of FIG. 13, columns of A and rows of B are input to the processing elements from the left and top respectively. The two data, Aij and Bij, are multiplied as they meet at a processing node and added to the product Cij; the data value currently residing in a register at a node. Note, that the initial value of the Cij register in all node is zero. When the register has been updated, the Aij and Bij data items are then passed to the next processor. As all the column and row data arrive at the processor nodes, all of the products of equation [1] will be sequentially summed. This design requires global communication to broadcast the row and column data, which cannot be accomplished by prior art systolic or wave array processors. There is also the additional problem of reading the result out of the array back to a host processor.
The product C can also be computed using the inner product accumulation:
C(0,i,j)=0
C(k,i,j)=C(k-1,i,j)+A(i,j)*B(j,i) For k=1,2 . . . , N.     [2]
One prior art implementation for matrix mutliplication using inner product accumulation is the systolic array shown in prior art FIG. 14. For the example problem, A is propagated into the left edge of the processors, B is propagated into the top edge of processors, and C (initially 0) is prorated diagonally through the array from the upper left corner. Global clocking of the array, used in the systolic array, requires each processing element to process data at each clock pulse. Thus, the different columns of B and rows of A have to be adjusted by the extra zeros shown, in order to arrive at each processing element at the correct time. As each set of A's arrive at a processor element, they are multiplied and added to the current partial sum in the processing element. The result is propagated out of the array on the bottom diagonal.
If readout of the products is ignored, successive products can be obtained in N cycles. But that is the problem! How does one readout the N products in the systolic array? The products can be shifted out, which requires additional processor cycles, each processor element can be interfaced to the host computer, which greatly adds to the complexity of the system, or the processors can be bused in rows or columns to the host. Thus, communication with the host is critical affecting the complexity of the system, data communication rate requirements, and the system throughput rate.
The wavefront array processor uses the concept of a computation wavefront traveling down the processor array. Each processor modifies a term in the wavefront and acts as a secondary source responsible for the propagation of the wavefront. Thus, a wavefront in the processing array corresponds to a mathematical recursion in the algorithm. Successive pipelining of the wavefronts computes all recursions in the algorithm.
A prior art Wavefront Array processor for matrix multiplication is shown in prior art FIG. 15. Note that memory 156, 158 in the prior art array is placed on the top and left sides of the array of processor. To implement matrix multiplication on this type of array, the registers of all the processing elements are initially set to zero:
C(0,ij)=0   for all i and j:
the entries for A(i,j) are stored in memories to the left (in columns), and the entries for B(i,j) are stored in memories on the top (in rows). The process starts with PE(1,1) where:
C(1,11)=C(0,11)+A11*B11
is computed. The computation wavefront then propagates to the neighboring PE's (1,2) and (2,1), which compute:
C(1,12)=C(0,12)+A11*B12
and
C(1,21)=C(0,21)+A21*B11
As this first wave propagates through the array, an identical second wavefront (recursion) can execute in parallel immediately after the first. Thus, at the same time PE(1,2) and PE(2,1) are computing C(1,12) and C(1,21) respectively, PE(1,1) computes:
C(2,11)+C(1,11)+A12*B21
This pipelining is feasible because the wavefronts of two successive recursions will never intersect. The processors executing the recursions at any given instant will be different; avoiding any contention problem. In fact, with the capability to propagate an initialization zero between problems, a second new multiplication problem can be started as soon as the first processing element has completed all recursions for the first problem.
FIGS. 16 and 17 illustrate that this matrix multiplication problem which is so difficult and cumbersome to handle on the systolic array or the prior art wavefront array can be simply handled on the MWAP architecture. In fact, whereas the prior art wavefront array processor requires a two-dimensional processing array, the problem can be handled by MWAP in a simple linear array. FIG. 16 illustrates that the multiplication can be accomplished in a three-processor linear array by storing data and coefficient in the dual port memory (PPM) between processing stages. Interleaved columns of the matrix B and rows of the matrix A shown are entered in reverse order from the bottom to the top of the matrix. The rows of matrix A are entered in reverse order from right to left. Each processing element computes one term of the partial sum for each output term C(ij) as they are prorated through the array. The computation sequence is outlined in FIG. 17.
Each processor element in the MWAP essentially does the computations of a vertical row of processors in the systolic or prior art wavefront implementation. This is made possible by holding coefficient in the dual-port memory linking elements between the processing elements. The first fourteen cycles shown in FIG. 17 are initialing the array by loading coefficients for the multiplication. The time to do this corresponds to the time required to load coefficients into the memories along the edge of a prior art wavefront array.
Computations begin flowing through the array on the 15th cycle. Note that once output starts on the 22nd cycle, results are stored in the last dual-port memory linking element every two processor cycles. From this point in time on, computation and output occur simultaneously. No additional time is required to read the results from the array, as was the case with the systolic array example. Pairs of matrices may be continuous entered from the left, with results read from the right of the MWAP array.
It can be seen in FIG. 17 that the computation time for each row of the output matrix is 2N+1 processor cycles, where N is the size of the square matrix. The total computation time for the multiplication of two square matrices of size N is N(2N+1) processor cycles. Thus, the computation time for N processors to compute an N X N product is approximately proportional to N squared. That this is approximately the same, or slightly better than, the performance obtained with a systolic or prior art wavefront array can be seen as follows: Assume one has nine processors to use in computing a 9×9 full matrix multiplication. If a linear MWAP array is used, it will require approximately 9(2*9+1) or 171 processor cycles. Using a systolic or prior art wavefront array requires that the product be done by matrix partitioning. Partitioning the A and B matrices into 3×3 matrices result in: ##EQU4## Where A(ij), B(ij), and C(i,j) are all 3×3 matrices.
As a N x N systolic or prior art wavefront array can compute a N x N matrix product in approximately N processor iterations, the computation of each C(ij) term will require 3*N or 9 processor iterations. Thus computation of the entire C matrix for prior art arrays will require 9×9 or 81 processor iterations plus the time required to perform 18 matrix additions. The basic iteration for matrix multiplication with a prior art wavefront array is:
FETCH B, UP
FETCH A, LEFT
FLOW A, RIGHT
FLOW B, DOWN
MULT A, B, D
ADD C, D, C
This iteration requires six processor cycles. The approximate time to compute the 9×9 matrix product is then 486 processor cycles using the prior art wavefront array. If the cycle time for the two processors is the same, the MWAP array is then approximately 2.5 times faster than the prior art wavefront array. The above comparison illustrates two additional properties of the MWAP:
7. The simultaneous computation and multidirectional communication capability of the MWAP yields a significant increase in its throughput rate. In fact, for most algorithms the MWAP will be faster than either a systolic or prior art wavefront array.
8. The use of linking memory permits a single linear MWAP array to implement a board variety of both 1-D and 2-D geometry algorithms.
Use of MWAP to Calculate Fast Fourier Transforms (FFT)
As discussed earlier, calculating the Fourier transform using the recursion formula is impossible using prior art systolic or wavefront array processing. The discrete Fourier transform defined by the equation, ##EQU5## can be calculated with a systolic or prior art wavefront array. However, the discrete formula is not as desirable as the recursion formula because it requires N processors and N processor cycles or N squared operations to compute a transform of length N.
The Fourier transform recursion formula is as follows: ##EQU6## with p, q and r varying from stage to stage. This Fast Fourier Transform, (FFT), calculation requires only N*log2 (N) operations to compute a transform of size N. Thus the recursion formula is faster than direct computation using the discrete Fourier transform. However, the distance between the input computation points changes (increases) for each stage in the computation using the recursion formula. This can be seen FIG. 18 which is a signal flow graph for the decimation-in-time constant-geometry FFT algorithm. This variation in the distance between input data points, or global communication requirement, makes it impossible to implement the FFT using the recursion formula on a systolic or prior art wavefront array.
One method using the MWAP for implementing the FFT using the recursion formula would be to use a processing element for each term in the algorithm with the processors interconnected as shown in FIG. 18. This would require N processors for a N point transform.
However, the same linear array Memory-Linked Wavefront Array Processor used in the previous examples can compute the Fast Fourier Transform. To implement the FFT on the MWAP, the input is stored in the first dual-port memory linking element in bit-reversed order, the W coefficients are stored in the dual-port memories linking elements between stages in bit-reversed order, and the sum and difference terms are propagated between processors using two base address registers. This makes the addressing of coefficients and data between stages linear, as can be seen in FIG. 19. The MWAP computes the FFT as follows:
1. Each stage of the FFT is implemented using one MWAP processing module which computes X(p)+W(r)*X(q) and X(p)-W*(r)X(q).
2. The processor at each stage alternates between using memory address register A and memory address register B to output |p-q| length blocks of sum and difference products to the dual-port memory linking elements to its right.
3. The processor at each stage reads computation points from the dual-port memory linking elements to its left alternately using memory address base resistor A and B.
The algorithm is illustrated in FIG. 19 with time snapshots of the computation of a 16-point FFT. The MWAP implements the FFT using 1n(N) processors for a size N transform and performs multiple Fourier Transforms, of length N, in N/2 systolic cycles. Thus, the MWAP architecture that can implement algorithms that are not possible with systolic or prior art wavefront arrays.
Obviously many modifications and variations of the present invention are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims the invention may be practiced otherwise than as specifically described.

Claims (24)

What is claimed is:
1. A memory linked wavefront array processor comprising:
a linear array of processing elements, each processing element having right and left independent ports,
a means for providing a dedicated data flow path with information storage between each pair of adjacent processing elements and permitting simultaneous data transfer between all adjacent processing elements, said means comprising,
a plurality of dual port memory linking means interspersed in said array between processing elements, each particular memory linking means connected to the right independent port of its left adjacent processing element and the left independent port of its right adjacent processing element for providing a dedicated data flow path with information storage between such adjacent processing elements; and,
a means for providing independent asynchronous local control of each processing element in said linear array, said means comprising,
at least two control flags corresponding with each dual port memory linking means for permitting control of overlapping data flow in that particular dual port memory linking means, and
a local control means within each particular processing element for (a) setting, resetting and testing a control flag corresponding with a dual port memory linking means adjacent to said particular processing element; (b) suspending execution of an instruction by said particular processing element when a tested control flag specified in the instruction is false and, (c) completing the instruction when said flag becomes true, so that the array processor is locally driven to process wavefronts of calculations passing through the array.
2. The processor of claim 1, wherein each control flag comprises a hardware circuit having two alternate states.
3. The processor of claim 1, wherein each processing element further comprises a right address register for addressing memory locations in its right adjacent dual port memory linking means and a left address register for addressing memory locations in its left adjacent dual port memory linking means.
4. The processor of claim 3, wherein said right address register comprises a plurality of right base registers with each right base register connected to a right address counter and each right address counter connected to an address bus of said right adjacent dual port memory linking means, wherein each right base register holds a reference memory address for its corresponding right address register, and wherein said left address register comprises a plurality of left base registers with each left base register connected to a left address counter and each left address counter connected to an address bus of said left adjacent dual port memory linking means, wherein said left base register holds a reference memory address for its corresponding left address counter, and wherein each processing element includes a program means with associated logic for sequencing operations of the particular processing element and for independently selecting between incrementing, resetting to the base address, and holding the current count for any particular address register, during the same instruction cycle that memory is required.
5. The processor of claim 4, wherein at least one of said address counters are connected to said address bus in bit reverse order.
6. The processor of claim 1, wherein each processing element includes a local clock, so that each processing element is self timed not requiring a global clock.
7. The processor of claim 1, further comprising:
an input interface having a first port coupled to a host computer and a second port coupled to a dual port memory linking means that is coupled to the first processing element in the array; and,
an output interface having a first port coupled to said host computer and a second port coupled to a dual port memory linking means that is coupled to the last processing element in the array.
8. The processor of claim 1, wherein each processing element further comprises:
input registers,
output register,
internal arithmetic registers, and wherein said right and left independent ports simultaneously connect to said input registers, output registers and internal arithmetic registers.
9. The processor of claim 8, wherein each processing element further comprises:
an arithmetic section comprising a multiplier and an adder/subtracter; and,
a bus structure means coupling said multiplier and said adder/subtracter to said internal registers for supporting simultaneous operation of said multiplier and said adder/subtracter.
10. The processor of claim 9, wherein each processing element further comprises a program memory with associated logic for sequencing the operation of said particular processing element and wherein said instruction words stored in said program memory to sequence the operation of said particular processing element have separate fields to control the multiplier, the adder/subtracter and read/write operations from said right and said left independent ports, wherein multiply, add/subtract and read/write to the left independent port and read/write to the right independent port can occur simultaneously during the same instruction cycle.
11. The processor of claim 1, wherein each processing element includes a program memory for storing several different program sequences for computing different algorithms, and a means for changing the starting address in each program memory, so that different processing elements in said linear array can perform different computations.
12. The processor of claim 1, wherein data and computation can be propagated of the right or left in said linear array of processing elements.
13. The processor of claim 1, wherein throughput can be increased by increasing the number of processing element/dual port memory linking pairs.
14. The processor of claim 1, wherein each dual port memory linking means comprises a means for loading and storing coefficients and other information between processing element stages in said array.
15. The processor of claim 1, wherein said memory linked waveform array processor is an n-dimensional structure wherein n is a positive integer defining the geometric dimension of said structure, and wherein said linear array of processing elements is a component of said n-dimensional structure.
16. A memory linked wavefront array processor comprising:
an array including (a) at least one interface (I) to a host computer, (b) a plurality of processing elements (PE), each processing element having two independent ports, and (c) a plurality of dual port memory elements (M), all interconnected in the form of {I, Mo, PEo . . . Mn, PEn }, where n is a positive integer and wherein each dual port memory element positioned between adjacent processing elements provides a dedicated data flow path with information storage between such processing elements; and,
a means for providing asynchronous local control of each processing element in said array, said means comprising,
at least two control flags corresponding with each dual port memory element for permitting control of overlapping data flow in that particular dual port memory linking elements, and
a local control means within each particular processing element for (a) setting, resetting and testing a control flag corresponding with a dual port memory element adjacent to said particular processing element; (b) suspending execution of an instruction by said particular processing element when a tested control flag specified in the instruction is false and, (c) completing the instruction when said flag becomes true, so that the array processor is locally driven to process wavefronts of calculations passing through the array.
17. The processor of claim 16, further comprising a second interface to said host computer having a first port connected to said host computer and a second port connected to a dual port memory element that is connected to an independent port of the last processing element (PEn) in said array.
18. The processor of claim 16, wherein each control flag comprises a hard wire circuit having two alternate states.
19. A memory-linked wavefront array processor comprising:
a two-dimensional structure of processing elements, each processing element having at least two independent data ports,
a plurality of memory linking means having at least two ports each particular memory linking means interspersed in said structure between adjacent processing elements and connected to an independent data port of such adjacent processing elements, for providing a dedicated data flow path with information storage between such adjacent processing element; and,
a means for providing independent asynchronous local control of each processing element in said structure, said means comprising,
at least two control flags corresponding with each memory linking means for permitting control of overlapping data flow in that particular memory linking means, and
a local control means within each particular processing element for (a) setting, resetting and testing a control flag corresponding with a memory linking means adjacent to said particular processing element; (b) suspending execution of an instruction by said particular processing element when a tested control flag specified in the instruction is false; and, (c) completing the instruction when said flag becomes true, so that said array processor is locally driven to process wavefronts of calculations passing through the array.
20. The processor of claim 19, wherein each control flag comprises a hardwire circuit having two alternate states.
21. The processor of claim 19, wherein said memory linking means is a dual port memory.
22. The processor of claim 19, further comprising:
an input interface having a first port coupled to a host computer, and a second port coupled to a memory linking means that is coupled to a first processing element within said structure; and,
an output interface having a first port coupled to said host computer, and a second port coupled to a memory linking means that is coupled to a second processing element within said structure.
23. A memory-linked wavefront array processor comprising:
a positive n-dimensional structure of processing elements, wherein n is an integer defining the geometric dimension of said structure, each processing element having at least two independent data ports,
a plurality of memory linking means having at least two ports, each particular memory linking means interspersed in said array between adjacent processing elements and connected to an independent data port of such adjacent processing elements, for providing a dedicated data flow path with information storage between such adjacent processing elements; and,
a means for providing independent asynchronous local control of each processing element in said structure, said means comprising,
at least two control flags corresponding with each memory linking means for permitting control of overlapping data flow in that particular memory linking means, and
a local control means within each particular processing element for (a) setting, resetting and testing a control flag corresponding with a memory linking means adjacent to said particular processing element; (b) suspending execution of an instruction by said particular processing element when a tested control flag specified in the instruction is false; and (c) completing the instruction when said flag becomes true, so that the array processor is locally driven to process wavefronts of calculations passing through the array.
24. The processor of claim 23, wherein each control flag comprises a hardware circuit having two alternate states.
US06/777,112 1985-09-17 1985-09-17 Memory-linked wavefront array processor Expired - Lifetime US4720780A (en)

Priority Applications (7)

Application Number Priority Date Filing Date Title
US06/777,112 US4720780A (en) 1985-09-17 1985-09-17 Memory-linked wavefront array processor
EP86906519A EP0237571B1 (en) 1985-09-17 1986-09-17 Memory-linked wavefront array processor
DE8686906519T DE3685107D1 (en) 1985-09-17 1986-09-17 MEMORY CONNECTOR WAVE FRONT FIELD PROCESSOR.
JP61505584A JPS63501530A (en) 1985-09-17 1986-09-17 Wavefront array processor with linked memory
PCT/US1986/001903 WO1987001841A1 (en) 1985-09-17 1986-09-17 Memory-linked wavefront array processor
KR1019870002221A KR970001899B1 (en) 1985-09-17 1987-03-12 Memory-linked wavefront array processor
US07/144,193 US4922418A (en) 1985-09-17 1988-01-15 Method for controlling propogation of data and transform through memory-linked wavefront array processor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US06/777,112 US4720780A (en) 1985-09-17 1985-09-17 Memory-linked wavefront array processor

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US07/144,193 Continuation US4922418A (en) 1985-09-17 1988-01-15 Method for controlling propogation of data and transform through memory-linked wavefront array processor

Publications (1)

Publication Number Publication Date
US4720780A true US4720780A (en) 1988-01-19

Family

ID=25109328

Family Applications (2)

Application Number Title Priority Date Filing Date
US06/777,112 Expired - Lifetime US4720780A (en) 1985-09-17 1985-09-17 Memory-linked wavefront array processor
US07/144,193 Expired - Lifetime US4922418A (en) 1985-09-17 1988-01-15 Method for controlling propogation of data and transform through memory-linked wavefront array processor

Family Applications After (1)

Application Number Title Priority Date Filing Date
US07/144,193 Expired - Lifetime US4922418A (en) 1985-09-17 1988-01-15 Method for controlling propogation of data and transform through memory-linked wavefront array processor

Country Status (6)

Country Link
US (2) US4720780A (en)
EP (1) EP0237571B1 (en)
JP (1) JPS63501530A (en)
KR (1) KR970001899B1 (en)
DE (1) DE3685107D1 (en)
WO (1) WO1987001841A1 (en)

Cited By (172)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4797806A (en) * 1987-02-19 1989-01-10 Gtx Corporation High speed serial pixel neighborhood processor and method
US4807183A (en) * 1985-09-27 1989-02-21 Carnegie-Mellon University Programmable interconnection chip for computer system functional modules
US4875207A (en) * 1986-01-30 1989-10-17 U.S. Philips Corporation A data processing network with chordal ring factor network
WO1989009967A1 (en) * 1988-04-08 1989-10-19 Cogent Research, Inc. Computing machine with hybrid communication architecture
US4876641A (en) * 1986-08-02 1989-10-24 Active Memory Technology Ltd. Vlsi data processor containing an array of ICs, each of which is comprised primarily of an array of processing
US4891751A (en) * 1987-03-27 1990-01-02 Floating Point Systems, Inc. Massively parallel vector processing computer
US4896265A (en) * 1988-03-28 1990-01-23 General Electric Company Parallel broadcasting method and apparatus
US4907148A (en) * 1985-11-13 1990-03-06 Alcatel U.S.A. Corp. Cellular array processor with individual cell-level data-dependent cell control and multiport input memory
US4908751A (en) * 1987-10-15 1990-03-13 Smith Harry F Parallel data processor
US4918596A (en) * 1985-07-01 1990-04-17 Akira Nakano Hierarchical information processing system
US4933895A (en) * 1987-07-10 1990-06-12 Hughes Aircraft Company Cellular array having data dependent processing capabilities
US4933836A (en) * 1986-10-29 1990-06-12 United Technologies Corporation n-Dimensional modular multiprocessor lattice architecture
US4975870A (en) * 1988-02-25 1990-12-04 Data General Corporation Apparatus for locking a portion of a computer memory
US4984192A (en) * 1988-12-02 1991-01-08 Ultrasystems Defense Inc. Programmable state machines connectable in a reconfiguration switching network for performing real-time data processing
US5012441A (en) * 1986-11-24 1991-04-30 Zoran Corporation Apparatus for addressing memory with data word and data block reversal capability
US5036454A (en) * 1987-05-01 1991-07-30 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of a loop with overlapped code
WO1991019256A1 (en) * 1990-05-30 1991-12-12 Adaptive Solutions, Inc. Mechanism providing concurrent computational/communications in simd architecture
WO1991019269A1 (en) * 1990-05-29 1991-12-12 Wavetracer, Inc. Multi-dimensional processor system and processor array with massively parallel input/output
US5083267A (en) * 1987-05-01 1992-01-21 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of an instruction loop with recurrance
US5115510A (en) * 1987-10-20 1992-05-19 Sharp Kabushiki Kaisha Multistage data flow processor with instruction packet, fetch, storage transmission and address generation controlled by destination information
US5121502A (en) * 1989-12-20 1992-06-09 Hewlett-Packard Company System for selectively communicating instructions from memory locations simultaneously or from the same memory locations sequentially to plurality of processing
US5133073A (en) * 1990-05-29 1992-07-21 Wavetracer, Inc. Processor array of N-dimensions which is physically reconfigurable into N-1
US5168572A (en) * 1989-03-10 1992-12-01 The Boeing Company System for dynamic selection of globally-determined optimal data path
US5175858A (en) * 1991-03-04 1992-12-29 Adaptive Solutions, Inc. Mechanism providing concurrent computational/communications in SIMD architecture
US5179530A (en) * 1989-11-03 1993-01-12 Zoran Corporation Architecture for integrated concurrent vector signal processor
US5193202A (en) * 1990-05-29 1993-03-09 Wavetracer, Inc. Processor array with relocated operand physical address generator capable of data transfer to distant physical processor for each virtual processor while simulating dimensionally larger array processor
US5197130A (en) * 1989-12-29 1993-03-23 Supercomputer Systems Limited Partnership Cluster architecture for a highly parallel scalar/vector multiprocessor system
US5206952A (en) * 1990-09-12 1993-04-27 Cray Research, Inc. Fault tolerant networking architecture
US5226128A (en) * 1987-05-01 1993-07-06 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of a loop with a branch
US5241492A (en) * 1991-05-06 1993-08-31 Motorola, Inc. Apparatus for performing multiply and accumulate instructions with reduced power and a method therefor
US5276819A (en) * 1987-05-01 1994-01-04 Hewlett-Packard Company Horizontal computer having register multiconnect for operand address generation during execution of iterations of a loop of program code
US5278781A (en) * 1987-11-12 1994-01-11 Matsushita Electric Industrial Co., Ltd. Digital signal processing system
US5349677A (en) * 1988-05-10 1994-09-20 Cray Research, Inc. Apparatus for calculating delay when executing vector tailgating instructions and using delay to facilitate simultaneous reading of operands from and writing of results to same vector register
US5410723A (en) * 1989-11-21 1995-04-25 Deutsche Itt Industries Gmbh Wavefront array processor for blocking the issuance of first handshake signal (req) by the presence of second handshake signal (ack) which indicates the readyness of the receiving cell
US5421019A (en) * 1988-10-07 1995-05-30 Martin Marietta Corporation Parallel data processor
US5428803A (en) * 1992-07-10 1995-06-27 Cray Research, Inc. Method and apparatus for a unified parallel processing architecture
US5465375A (en) * 1992-01-14 1995-11-07 France Telecom Multiprocessor system with cascaded modules combining processors through a programmable logic cell array
US5485576A (en) * 1994-01-28 1996-01-16 Fee; Brendan Chassis fault tolerant system management bus architecture for a networking
US5489949A (en) * 1992-02-08 1996-02-06 Samsung Electronics Co., Ltd. Method and apparatus for motion estimation
US5506992A (en) * 1992-01-30 1996-04-09 Saxenmeyer; George Distributed processing system with asynchronous communication between processing modules
US5555386A (en) * 1992-11-26 1996-09-10 Sharp Kabushiki Kaisha Data flow processor with variable logic connection between processors in a system
US5581767A (en) * 1993-06-16 1996-12-03 Nippon Sheet Glass Co., Ltd. Bus structure for multiprocessor system having separated processor section and control/memory section
US5588152A (en) * 1990-11-13 1996-12-24 International Business Machines Corporation Advanced parallel processor including advanced support hardware
US5594918A (en) * 1991-05-13 1997-01-14 International Business Machines Corporation Parallel computer system providing multi-ported intelligent memory
US5600799A (en) * 1990-04-27 1997-02-04 National Semiconductor Corporation Status batching and filtering in a media access control/host system interface unit
US5617577A (en) * 1990-11-13 1997-04-01 International Business Machines Corporation Advanced parallel array processor I/O connection
US5623689A (en) * 1991-07-16 1997-04-22 Matsushita Electric Industrial Co., Ltd. Parallel processor system for quickly detecting the termination of data transmission
US5625836A (en) * 1990-11-13 1997-04-29 International Business Machines Corporation SIMD/MIMD processing memory element (PME)
US5630162A (en) * 1990-11-13 1997-05-13 International Business Machines Corporation Array processor dotted communication network based on H-DOTs
US5689450A (en) * 1994-08-30 1997-11-18 Sony Corporation Parallel processor
US5708836A (en) * 1990-11-13 1998-01-13 International Business Machines Corporation SIMD/MIMD inter-processor communication
US5708847A (en) * 1994-05-19 1998-01-13 Yamaha Corporation Method of digital signal processing and apparatus using a reference operation cycle including a processing period and a transfer period
US5710935A (en) * 1990-11-13 1998-01-20 International Business Machines Corporation Advanced parallel array processor (APAP)
US5717944A (en) * 1990-11-13 1998-02-10 International Business Machines Corporation Autonomous SIMD/MIMD processor memory elements
US5734921A (en) * 1990-11-13 1998-03-31 International Business Machines Corporation Advanced parallel array processor computer package
US5748872A (en) * 1994-03-22 1998-05-05 Norman; Richard S. Direct replacement cell fault tolerant architecture
US5754596A (en) * 1994-02-23 1998-05-19 Rosemount Inc. Field transmitter for storing information
US5765012A (en) * 1990-11-13 1998-06-09 International Business Machines Corporation Controller for a SIMD/MIMD array having an instruction sequencer utilizing a canned routine library
US5765015A (en) * 1990-11-13 1998-06-09 International Business Machines Corporation Slide network for an array processor
US5794059A (en) * 1990-11-13 1998-08-11 International Business Machines Corporation N-dimensional modified hypercube
US5801715A (en) * 1991-12-06 1998-09-01 Norman; Richard S. Massively-parallel processor array with outputs from individual processors directly to an external device without involving other processors or a common physical carrier
US5805915A (en) * 1992-05-22 1998-09-08 International Business Machines Corporation SIMIMD array processing system
US5809292A (en) * 1990-11-13 1998-09-15 International Business Machines Corporation Floating point for simid array machine
US5815723A (en) * 1990-11-13 1998-09-29 International Business Machines Corporation Picket autonomy on a SIMD machine
US5822608A (en) * 1990-11-13 1998-10-13 International Business Machines Corporation Associative parallel processing system
US5828894A (en) * 1990-11-13 1998-10-27 International Business Machines Corporation Array processor having grouping of SIMD pickets
US5949440A (en) * 1996-04-30 1999-09-07 Hewlett Packard Compnay Method and apparatus for processing graphics primitives in multiple modes using reconfigurable hardware
US5963745A (en) * 1990-11-13 1999-10-05 International Business Machines Corporation APAP I/O programmable router
US5963746A (en) * 1990-11-13 1999-10-05 International Business Machines Corporation Fully distributed processing memory element
US5966528A (en) * 1990-11-13 1999-10-12 International Business Machines Corporation SIMD/MIMD array processor with vector processing
US5991866A (en) * 1992-03-25 1999-11-23 Tm Patents, Lp Method and system for generating a program to facilitate rearrangement of address bits among addresses in a massively parallel processor system
US6003098A (en) * 1996-04-30 1999-12-14 Hewlett-Packard Company Graphic accelerator architecture using two graphics processing units for processing aspects of pre-rasterized graphics primitives and a control circuitry for relaying pass-through information
US6067609A (en) * 1998-04-09 2000-05-23 Teranex, Inc. Pattern generation and shift plane operations for a mesh connected computer
US6073185A (en) * 1993-08-27 2000-06-06 Teranex, Inc. Parallel data processor
US6104439A (en) * 1992-02-08 2000-08-15 Samsung Electronics Co., Ltd. Method and apparatus for motion estimation
US6145071A (en) * 1994-03-03 2000-11-07 The George Washington University Multi-layer multi-processor information conveyor with periodic transferring of processors' states for on-the-fly transformation of continuous information flows and operating method therefor
US6173388B1 (en) 1998-04-09 2001-01-09 Teranex Inc. Directly accessing local memories of array processors for improved real-time corner turning processing
US6185667B1 (en) 1998-04-09 2001-02-06 Teranex, Inc. Input/output support for processing in a mesh connected computer
US6212628B1 (en) 1998-04-09 2001-04-03 Teranex, Inc. Mesh connected computer
WO2001031473A1 (en) * 1999-10-26 2001-05-03 Arthur D. Little, Inc. Multiplexing n-dimensional mesh connections onto (n + 1) data paths
US6300793B1 (en) 1995-05-03 2001-10-09 Btr, Inc. Scalable multiple level tab oriented interconnect architecture
US6320412B1 (en) 1999-12-20 2001-11-20 Btr, Inc. C/O Corporate Trust Co. Architecture and interconnect for programmable logic circuits
US6329839B1 (en) 1996-09-04 2001-12-11 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US20020070756A1 (en) * 1995-05-03 2002-06-13 Ting Benjamins S. Floor plan for scalable multiple level tab oriented interconnect architecture
US6421772B1 (en) * 1998-06-04 2002-07-16 Kabushiki Kaisha Toshiba Parallel computer with improved access to adjacent processor and memory elements
US6462578B2 (en) 1993-08-03 2002-10-08 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US6502180B1 (en) * 1997-09-12 2002-12-31 California Institute Of Technology Asynchronous circuits with pipelined completion process
US6507217B2 (en) 1993-08-03 2003-01-14 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US20030046607A1 (en) * 2001-09-03 2003-03-06 Frank May Method for debugging reconfigurable architectures
US20030056085A1 (en) * 1996-12-09 2003-03-20 Entire Interest Unit for processing numeric and logic operations for use in central processing units (CPUS), multiprocessor systems, data-flow processors (DSPS), systolic processors and field programmable gate arrays (FPGAS)
US20030093662A1 (en) * 1996-12-27 2003-05-15 Pact Gmbh Process for automatic dynamic reloading of data flow processors (DFPS) and units with two- or three-dimensional programmable cell architectures (FPGAS, DPGAS, and the like)
US20030135686A1 (en) * 1997-02-11 2003-07-17 Martin Vorbach Internal bus system for DFPs and units with two- or multi-dimensional programmable cell architectures, for managing large volumes of data with a high interconnection complexity
US6624658B2 (en) 1999-02-04 2003-09-23 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US6636986B2 (en) 1994-03-22 2003-10-21 Hyperchip Inc. Output and/or input coordinated processing array
US20040015899A1 (en) * 2000-10-06 2004-01-22 Frank May Method for processing data
US20040030859A1 (en) * 2002-06-26 2004-02-12 Doerr Michael B. Processing system with interspersed processors and communication elements
US6701432B1 (en) * 1999-04-01 2004-03-02 Netscreen Technologies, Inc. Firewall including local bus
US20040052130A1 (en) * 1997-02-08 2004-03-18 Martin Vorbach Method of self-synchronization of configurable elements of a programmable unit
US6728863B1 (en) 1999-10-26 2004-04-27 Assabet Ventures Wide connections for transferring data between PE's of an N-dimensional mesh-connected SIMD array while transferring operands from memory
US20040083399A1 (en) * 1997-02-08 2004-04-29 Martin Vorbach Method of self-synchronization of configurable elements of a programmable module
US6754801B1 (en) * 2000-08-22 2004-06-22 Micron Technology, Inc. Method and apparatus for a shift register based interconnection for a massively parallel processor array
US20040181726A1 (en) * 1997-12-22 2004-09-16 Martin Vorbach Method and system for alternating between programs for execution by cells of an integrated circuit
US20040243984A1 (en) * 2001-06-20 2004-12-02 Martin Vorbach Data processing method
US20040249880A1 (en) * 2001-12-14 2004-12-09 Martin Vorbach Reconfigurable system
US20040255096A1 (en) * 2003-06-11 2004-12-16 Norman Richard S. Method for continuous linear production of integrated circuits
US6859869B1 (en) * 1995-11-17 2005-02-22 Pact Xpp Technologies Ag Data processing system
US20050053056A1 (en) * 2001-09-03 2005-03-10 Martin Vorbach Router
US20050066213A1 (en) * 2001-03-05 2005-03-24 Martin Vorbach Methods and devices for treating and processing data
US20050132344A1 (en) * 2002-01-18 2005-06-16 Martin Vorbach Method of compilation
US20050223212A1 (en) * 2000-06-13 2005-10-06 Martin Vorbach Pipeline configuration protocol and configuration unit communication
US20050218928A1 (en) * 2004-03-30 2005-10-06 Pani Peter M Scalable non-blocking switching network for programmable logic
US6990555B2 (en) 2001-01-09 2006-01-24 Pact Xpp Technologies Ag Method of hierarchical caching of configuration data having dataflow processors and modules having two- or multidimensional programmable cell structure (FPGAs, DPGAs, etc.)
US20060023704A1 (en) * 2004-07-29 2006-02-02 Pani Peter M Interconnection fabric using switching networks in hierarchy
US20060031659A1 (en) * 2004-08-09 2006-02-09 Arches Computing Systems Multi-processor reconfigurable computing system
US20060031595A1 (en) * 1996-12-27 2006-02-09 Martin Vorbach Process for automatic dynamic reloading of data flow processors (DFPs) and units with two- or three-dimensional programmable cell architectures (FPGAs, DPGAs, and the like
US20060075211A1 (en) * 2002-03-21 2006-04-06 Martin Vorbach Method and device for data processing
US20060090062A1 (en) * 2002-01-19 2006-04-27 Martin Vorbach Reconfigurable processor
US20060155956A1 (en) * 2003-01-27 2006-07-13 Nolan John M Processor array
US20060192586A1 (en) * 2002-09-06 2006-08-31 Martin Vorbach Reconfigurable sequencer structure
US20060248317A1 (en) * 2002-08-07 2006-11-02 Martin Vorbach Method and device for processing data
US20070011433A1 (en) * 2003-04-04 2007-01-11 Martin Vorbach Method and device for data processing
US7174443B1 (en) 1996-12-20 2007-02-06 Pact Xpp Technologies Ag Run-time reconfiguration method for programmable units
US20070033379A1 (en) * 2003-03-31 2007-02-08 Graham Kirsch Active memory processing array topography and method
US20070050603A1 (en) * 2002-08-07 2007-03-01 Martin Vorbach Data processing method and device
US20070061661A1 (en) * 2005-07-06 2007-03-15 Stmicroelectronics S.A. Bit rate adaptation in a data processing flow
US20070083730A1 (en) * 2003-06-17 2007-04-12 Martin Vorbach Data processing device and method
US7210129B2 (en) 2001-08-16 2007-04-24 Pact Xpp Technologies Ag Method for translating programs for reconfigurable architectures
US20070113046A1 (en) * 2001-03-05 2007-05-17 Martin Vorbach Data processing device and method
US20070123091A1 (en) * 2005-11-18 2007-05-31 Swedberg Benjamin D Releasable Wire Connector
US20070226686A1 (en) * 2006-03-27 2007-09-27 Beardslee John M Programming a multi-processor system
US20080140980A1 (en) * 2005-06-30 2008-06-12 Interuniversitair Microelektronica Centrum (Imec) Vzw Memory arrangement for multi-processor systems
US7423453B1 (en) 2006-01-20 2008-09-09 Advantage Logic, Inc. Efficient integrated circuit layout scheme to implement a scalable switching network used in interconnection fabric
US20080222329A1 (en) * 1996-12-20 2008-09-11 Martin Vorbach I/O and memory bus system for DFPs and units with two- or multi-dimensional programmable cell architectures
US20080263118A1 (en) * 2007-04-06 2008-10-23 Montvelishsky Michael B System for convolution calculation with multiple computer processors
US20080278678A1 (en) * 2003-10-09 2008-11-13 Howell Thomas A Eyeglasses with user monitoring
US7457234B1 (en) 2003-05-14 2008-11-25 Adtran, Inc. System and method for protecting communication between a central office and a remote premises
US20090031104A1 (en) * 2005-02-07 2009-01-29 Martin Vorbach Low Latency Massive Parallel Data Processing Device
US20090149211A1 (en) * 2007-11-05 2009-06-11 Picochip Designs Limited Power control
US20090146691A1 (en) * 2000-10-06 2009-06-11 Martin Vorbach Logic cell array and bus system
US20090158007A1 (en) * 2007-12-12 2009-06-18 Itt Manufacturing Enterprises, Inc. Scaleable array of micro-engines for waveform processing
US20090172351A1 (en) * 2003-08-28 2009-07-02 Martin Vorbach Data processing device and method
US20090182993A1 (en) * 2007-12-13 2009-07-16 Karl Fant Concurrent processing element system, and method
US20090210653A1 (en) * 2001-03-05 2009-08-20 Pact Xpp Technologies Ag Method and device for treating and processing data
US7581076B2 (en) 2001-03-05 2009-08-25 Pact Xpp Technologies Ag Methods and devices for treating and/or processing data
US7595659B2 (en) 2000-10-09 2009-09-29 Pact Xpp Technologies Ag Logic cell array and bus system
US20090300262A1 (en) * 2001-03-05 2009-12-03 Martin Vorbach Methods and devices for treating and/or processing data
US20100153654A1 (en) * 2002-08-07 2010-06-17 Martin Vorbach Data processing method and device
US20100228918A1 (en) * 1999-06-10 2010-09-09 Martin Vorbach Configurable logic integrated circuit having a multidimensional structure of configurable elements
US7823195B1 (en) * 1999-04-01 2010-10-26 Juniper Networks, Inc. Method, apparatus and computer program product for a network firewall
US20100327907A1 (en) * 2009-06-24 2010-12-30 Ting Benjamin S Enhanced permutable switching network with multicasting signals for interconnection fabric
US20110002426A1 (en) * 2009-01-05 2011-01-06 Picochip Designs Limited Rake Receiver
US20110060942A1 (en) * 2001-03-05 2011-03-10 Martin Vorbach Methods and devices for treating and/or processing data
US7996827B2 (en) 2001-08-16 2011-08-09 Martin Vorbach Method for the translation of programs for reconfigurable architectures
US20110238948A1 (en) * 2002-08-07 2011-09-29 Martin Vorbach Method and device for coupling a data processing unit and a data processing array
US8127061B2 (en) 2002-02-18 2012-02-28 Martin Vorbach Bus systems and reconfiguration methods
US8250503B2 (en) 2006-01-18 2012-08-21 Martin Vorbach Hardware definition method including determining whether to implement a function as hardware or software
US8463312B2 (en) 2009-06-05 2013-06-11 Mindspeed Technologies U.K., Limited Method and device in a communication network
US8686475B2 (en) 2001-09-19 2014-04-01 Pact Xpp Technologies Ag Reconfigurable elements
US8686549B2 (en) 2001-09-03 2014-04-01 Martin Vorbach Reconfigurable elements
US8712469B2 (en) 2011-05-16 2014-04-29 Mindspeed Technologies U.K., Limited Accessing a base station
US20140173253A1 (en) * 2003-09-08 2014-06-19 Altera Corporation Methods and Apparatus for Storing Expanded Width Instructions in a VLIW Memory for Deferred Execution
US8798630B2 (en) 2009-10-05 2014-08-05 Intel Corporation Femtocell base station
US8849340B2 (en) 2009-05-07 2014-09-30 Intel Corporation Methods and devices for reducing interference in an uplink
US8862076B2 (en) 2009-06-05 2014-10-14 Intel Corporation Method and device in a communication network
US8880866B2 (en) 2010-10-15 2014-11-04 Coherent Logix, Incorporated Method and system for disabling communication paths in a multiprocessor fabric by setting register values to disable the communication paths specified by a configuration
US8904148B2 (en) 2000-12-19 2014-12-02 Intel Corporation Processor architecture with switch matrices for transferring data along buses
US9042434B2 (en) 2011-04-05 2015-05-26 Intel Corporation Filter
US9107136B2 (en) 2010-08-16 2015-08-11 Intel Corporation Femtocell access control
US20180336163A1 (en) * 2017-05-17 2018-11-22 Google Llc Low latency matrix multiply unit
US10856302B2 (en) 2011-04-05 2020-12-01 Intel Corporation Multimode base station
US20220405060A1 (en) * 2019-08-19 2022-12-22 Vorticity Inc. Systolic array design for solving partial differential equations
US11656849B2 (en) 2019-08-14 2023-05-23 Vorticity Inc. Dedicated hardware system for solving partial differential equations

Families Citing this family (68)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0576749B1 (en) * 1992-06-30 1999-06-02 Discovision Associates Data pipeline system
CA1283738C (en) * 1985-11-13 1991-04-30 Atsushi Hasebe Data processor
GB2211638A (en) * 1987-10-27 1989-07-05 Ibm Simd array processor
JPH0254383A (en) * 1988-08-18 1990-02-23 Mitsubishi Electric Corp Array processor
DE68920388T2 (en) * 1988-09-19 1995-05-11 Fujitsu Ltd Parallel computer system using a SIMD process.
JPH02178808A (en) * 1988-12-29 1990-07-11 Yaskawa Electric Mfg Co Ltd Robot control method
US5072371A (en) * 1989-03-01 1991-12-10 The United States Of America As Represented By The United States Department Of Energy Method for simultaneous overlapped communications between neighboring processors in a multiple
US5689647A (en) * 1989-03-14 1997-11-18 Sanyo Electric Co., Ltd. Parallel computing system with processing element number setting mode and shortest route determination with matrix size information
US5101480A (en) * 1989-05-09 1992-03-31 The University Of Michigan Hexagonal mesh multiprocessor system
US5142686A (en) * 1989-10-20 1992-08-25 United Technologies Corporation Multiprocessor system having processors and switches with each pair of processors connected through a single switch using Latin square matrix
GB9008366D0 (en) * 1990-04-12 1990-06-13 British Aerospace Data interaction architecture(dia)for real time embedded multi processor systems
US5430862A (en) * 1990-06-29 1995-07-04 Bull Hn Information Systems Inc. Emulation of CISC instructions by RISC instructions using two pipelined stages for overlapped CISC decoding and RISC execution
GB9018048D0 (en) * 1990-08-16 1990-10-03 Secr Defence Digital processor for simulating operation of a parallel processing array
JP3237858B2 (en) * 1991-01-30 2001-12-10 沖電気工業株式会社 Arithmetic unit
US5434970A (en) * 1991-02-14 1995-07-18 Cray Research, Inc. System for distributed multiprocessor communication
JPH04293151A (en) * 1991-03-20 1992-10-16 Fujitsu Ltd Parallel data processing system
US5361370A (en) * 1991-10-24 1994-11-01 Intel Corporation Single-instruction multiple-data processor having dual-ported local memory architecture for simultaneous data transmission on local memory ports and global port
JP2572522B2 (en) * 1992-05-12 1997-01-16 インターナショナル・ビジネス・マシーンズ・コーポレイション Computing device
US5842033A (en) * 1992-06-30 1998-11-24 Discovision Associates Padding apparatus for passing an arbitrary number of bits through a buffer in a pipeline system
US6330665B1 (en) 1992-06-30 2001-12-11 Discovision Associates Video parser
US6112017A (en) * 1992-06-30 2000-08-29 Discovision Associates Pipeline processing machine having a plurality of reconfigurable processing stages interconnected by a two-wire interface bus
US6079009A (en) * 1992-06-30 2000-06-20 Discovision Associates Coding standard token in a system compromising a plurality of pipeline stages
US7095783B1 (en) 1992-06-30 2006-08-22 Discovision Associates Multistandard video decoder and decompression system for processing encoded bit streams including start codes and methods relating thereto
US5768561A (en) * 1992-06-30 1998-06-16 Discovision Associates Tokens-based adaptive video processing arrangement
US6047112A (en) * 1992-06-30 2000-04-04 Discovision Associates Technique for initiating processing of a data stream of encoded video information
US5809270A (en) * 1992-06-30 1998-09-15 Discovision Associates Inverse quantizer
US6067417A (en) * 1992-06-30 2000-05-23 Discovision Associates Picture start token
US5835740A (en) * 1992-06-30 1998-11-10 Discovision Associates Data pipeline system and data encoding method
US6098113A (en) * 1992-10-22 2000-08-01 Ncr Corporation Apparatus and method for address translation and allocation for a plurality of input/output (I/O) buses to a system bus
US5586281A (en) * 1992-10-27 1996-12-17 Sharp Kabushiki Kaisha Data driven type information processing apparatus
JPH06290158A (en) * 1993-03-31 1994-10-18 Fujitsu Ltd Reconstructible torus network system
US5861894A (en) * 1993-06-24 1999-01-19 Discovision Associates Buffer manager
US5805914A (en) * 1993-06-24 1998-09-08 Discovision Associates Data pipeline system and data encoding method
US5848276A (en) * 1993-12-06 1998-12-08 Cpu Technology, Inc. High speed, direct register access operation for parallel processing units
US5801973A (en) * 1994-07-29 1998-09-01 Discovision Associates Video decompression
KR100186918B1 (en) 1994-10-21 1999-05-01 모리시다 요이치 Signal processor
US5548788A (en) * 1994-10-27 1996-08-20 Emc Corporation Disk controller having host processor controls the time for transferring data to disk drive by modifying contents of the memory to indicate data is stored in the memory
US6128689A (en) * 1997-04-14 2000-10-03 Hms Fieldbus Systems Ab System for exchanging data through data memory area of common memory in synchronous and asynchronous modes
US6088800A (en) 1998-02-27 2000-07-11 Mosaid Technologies, Incorporated Encryption processor with shared memory interconnect
US6513108B1 (en) * 1998-06-29 2003-01-28 Cisco Technology, Inc. Programmable processing engine for efficiently processing transient data
US6173386B1 (en) 1998-12-14 2001-01-09 Cisco Technology, Inc. Parallel processor with debug capability
US6920562B1 (en) 1998-12-18 2005-07-19 Cisco Technology, Inc. Tightly coupled software protocol decode with hardware data encryption
GB9911890D0 (en) * 1999-05-22 1999-07-21 Lucas Ind Plc Method and apparatus for detecting a fault condition in a computer processor
US6529983B1 (en) 1999-11-03 2003-03-04 Cisco Technology, Inc. Group and virtual locking mechanism for inter processor synchronization
US6584581B1 (en) * 1999-12-06 2003-06-24 Ab Initio Software Corporation Continuous flow checkpointing data processing
US6892237B1 (en) 2000-03-28 2005-05-10 Cisco Technology, Inc. Method and apparatus for high-speed parsing of network messages
US6505269B1 (en) 2000-05-16 2003-01-07 Cisco Technology, Inc. Dynamic addressing mapping to eliminate memory resource contention in a symmetric multiprocessor system
US7447872B2 (en) * 2002-05-30 2008-11-04 Cisco Technology, Inc. Inter-chip processor control plane communication
US7167850B2 (en) * 2002-10-10 2007-01-23 Ab Initio Software Corporation Startup and control of graph-based computation
GB2402760B (en) * 2003-06-12 2006-01-11 Advanced Risc Mach Ltd Improvements in flexibility of use of a data processing apparatus
US7130986B2 (en) * 2003-06-30 2006-10-31 Intel Corporation Determining if a register is ready to exchange data with a processing element
US7320064B2 (en) * 2004-07-23 2008-01-15 Honeywell International Inc. Reconfigurable computing architecture for space applications
US7478222B2 (en) * 2005-03-29 2009-01-13 Karl M. Fant Programmable pipeline array
US7877350B2 (en) 2005-06-27 2011-01-25 Ab Initio Technology Llc Managing metadata for graph-based computations
US20070046781A1 (en) * 2005-08-29 2007-03-01 Honeywell International Inc. Systems and methods for processing digital video data
EP2050013A4 (en) 2006-08-10 2010-01-06 Ab Initio Software Llc Distributing services in graph-based computations
CA2965896C (en) 2007-07-26 2020-01-07 Ab Initio Technology Llc Transactional graph-based computation with error handling
EP2396724A4 (en) * 2009-02-13 2012-12-12 Ab Initio Technology Llc Managing task execution
US8667329B2 (en) * 2009-09-25 2014-03-04 Ab Initio Technology Llc Processing transactions in graph-based applications
WO2011105408A1 (en) * 2010-02-24 2011-09-01 日本電気株式会社 Simd processor
CN107066241B (en) 2010-06-15 2021-03-09 起元技术有限责任公司 System and method for dynamically loading graph-based computations
US8924455B1 (en) * 2011-02-25 2014-12-30 Xilinx, Inc. Multiplication of matrices using systolic arrays
US9507682B2 (en) 2012-11-16 2016-11-29 Ab Initio Technology Llc Dynamic graph performance monitoring
US10108521B2 (en) 2012-11-16 2018-10-23 Ab Initio Technology Llc Dynamic component performance monitoring
US9274926B2 (en) 2013-01-03 2016-03-01 Ab Initio Technology Llc Configurable testing of computer programs
US9886241B2 (en) 2013-12-05 2018-02-06 Ab Initio Technology Llc Managing interfaces for sub-graphs
US10657134B2 (en) 2015-08-05 2020-05-19 Ab Initio Technology Llc Selecting queries for execution on a stream of real-time data
KR102051768B1 (en) 2015-12-21 2019-12-03 아브 이니티오 테크놀로지 엘엘시 Create sub-graph interface

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4065808A (en) * 1975-01-25 1977-12-27 U.S. Philips Corporation Network computer system
US4466064A (en) * 1980-05-14 1984-08-14 U.S. Philips Corporation Multiprocessor computer system for executing a splittable algorithm, notably a recursive algorithm
US4489381A (en) * 1982-08-06 1984-12-18 International Business Machines Corporation Hierarchical memories having two ports at each subordinate memory level
US4495567A (en) * 1981-10-15 1985-01-22 Codex Corporation Multiprocessor/multimemory control system
US4498134A (en) * 1982-01-26 1985-02-05 Hughes Aircraft Company Segregator functional plane for use in a modular array processor
US4507726A (en) * 1982-01-26 1985-03-26 Hughes Aircraft Company Array processor architecture utilizing modular elemental processors
US4509187A (en) * 1982-06-14 1985-04-02 At&T Bell Laboratories Time warp signal recognition processor using recirculating and/or reduced array of processor cells
US4514807A (en) * 1980-05-21 1985-04-30 Tatsuo Nogi Parallel computer
US4524455A (en) * 1981-06-01 1985-06-18 Environmental Research Inst. Of Michigan Pipeline processor
US4524428A (en) * 1982-01-26 1985-06-18 Hughes Aircraft Company Modular input-programmable logic circuits for use in a modular array processor
US4533993A (en) * 1981-08-18 1985-08-06 National Research Development Corp. Multiple processing cell digital data processor
US4543642A (en) * 1982-01-26 1985-09-24 Hughes Aircraft Company Data Exchange Subsystem for use in a modular array processor
US4550437A (en) * 1981-06-19 1985-10-29 Hitachi, Ltd. Apparatus for parallel processing of local image data
US4553203A (en) * 1982-09-28 1985-11-12 Trw Inc. Easily schedulable horizontal computer
US4580215A (en) * 1983-03-08 1986-04-01 Itt Corporation Associative array with five arithmetic paths
US4591980A (en) * 1984-02-16 1986-05-27 Xerox Corporation Adaptive self-repairing processor array
US4600992A (en) * 1982-12-14 1986-07-15 Honeywell Information Systems Inc. Priority resolver with lowest priority level having shortest logic path
US4636942A (en) * 1983-04-25 1987-01-13 Cray Research, Inc. Computer vector multiprocessing control
US4644496A (en) * 1983-01-11 1987-02-17 Iowa State University Research Foundation, Inc. Apparatus, methods, and systems for computer information transfer

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3737866A (en) * 1971-07-27 1973-06-05 Data General Corp Data storage and retrieval system
US3848234A (en) * 1973-04-04 1974-11-12 Sperry Rand Corp Multi-processor system with multiple cache memories
US4065809A (en) * 1976-05-27 1977-12-27 Tokyo Shibaura Electric Co., Ltd. Multi-processing system for controlling microcomputers and memories
US4309691A (en) * 1978-02-17 1982-01-05 California Institute Of Technology Step-oriented pipeline data processing system
US4184200A (en) * 1978-04-26 1980-01-15 Sperry Rand Corporation Integrating I/O element
US4574350A (en) * 1982-05-19 1986-03-04 At&T Bell Laboratories Shared resource locking apparatus
US4680698A (en) * 1982-11-26 1987-07-14 Inmos Limited High density ROM in separate isolation well on single with chip

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4065808A (en) * 1975-01-25 1977-12-27 U.S. Philips Corporation Network computer system
US4466064A (en) * 1980-05-14 1984-08-14 U.S. Philips Corporation Multiprocessor computer system for executing a splittable algorithm, notably a recursive algorithm
US4514807A (en) * 1980-05-21 1985-04-30 Tatsuo Nogi Parallel computer
US4524455A (en) * 1981-06-01 1985-06-18 Environmental Research Inst. Of Michigan Pipeline processor
US4550437A (en) * 1981-06-19 1985-10-29 Hitachi, Ltd. Apparatus for parallel processing of local image data
US4639857A (en) * 1981-08-18 1987-01-27 The Secretary Of State For Defence In Her Britannic Majesty's Government Of The United Kingdom Of Great Britain And Northern Ireland Digital data processor incorporating an orthogonally connected logic cell array
US4533993A (en) * 1981-08-18 1985-08-06 National Research Development Corp. Multiple processing cell digital data processor
US4495567A (en) * 1981-10-15 1985-01-22 Codex Corporation Multiprocessor/multimemory control system
US4507726A (en) * 1982-01-26 1985-03-26 Hughes Aircraft Company Array processor architecture utilizing modular elemental processors
US4524428A (en) * 1982-01-26 1985-06-18 Hughes Aircraft Company Modular input-programmable logic circuits for use in a modular array processor
US4543642A (en) * 1982-01-26 1985-09-24 Hughes Aircraft Company Data Exchange Subsystem for use in a modular array processor
US4498134A (en) * 1982-01-26 1985-02-05 Hughes Aircraft Company Segregator functional plane for use in a modular array processor
US4509187A (en) * 1982-06-14 1985-04-02 At&T Bell Laboratories Time warp signal recognition processor using recirculating and/or reduced array of processor cells
US4489381A (en) * 1982-08-06 1984-12-18 International Business Machines Corporation Hierarchical memories having two ports at each subordinate memory level
US4553203A (en) * 1982-09-28 1985-11-12 Trw Inc. Easily schedulable horizontal computer
US4600992A (en) * 1982-12-14 1986-07-15 Honeywell Information Systems Inc. Priority resolver with lowest priority level having shortest logic path
US4644496A (en) * 1983-01-11 1987-02-17 Iowa State University Research Foundation, Inc. Apparatus, methods, and systems for computer information transfer
US4580215A (en) * 1983-03-08 1986-04-01 Itt Corporation Associative array with five arithmetic paths
US4636942A (en) * 1983-04-25 1987-01-13 Cray Research, Inc. Computer vector multiprocessing control
US4591980A (en) * 1984-02-16 1986-05-27 Xerox Corporation Adaptive self-repairing processor array

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Danielsson et al., "Computer Structure for Image Processing", Academic Press, 1983, pp. 157-178.
Danielsson et al., Computer Structure for Image Processing , Academic Press, 1983, pp. 157 178. *

Cited By (365)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4918596A (en) * 1985-07-01 1990-04-17 Akira Nakano Hierarchical information processing system
US4807183A (en) * 1985-09-27 1989-02-21 Carnegie-Mellon University Programmable interconnection chip for computer system functional modules
US4907148A (en) * 1985-11-13 1990-03-06 Alcatel U.S.A. Corp. Cellular array processor with individual cell-level data-dependent cell control and multiport input memory
US4875207A (en) * 1986-01-30 1989-10-17 U.S. Philips Corporation A data processing network with chordal ring factor network
US4876641A (en) * 1986-08-02 1989-10-24 Active Memory Technology Ltd. Vlsi data processor containing an array of ICs, each of which is comprised primarily of an array of processing
US4933836A (en) * 1986-10-29 1990-06-12 United Technologies Corporation n-Dimensional modular multiprocessor lattice architecture
US5012441A (en) * 1986-11-24 1991-04-30 Zoran Corporation Apparatus for addressing memory with data word and data block reversal capability
US4797806A (en) * 1987-02-19 1989-01-10 Gtx Corporation High speed serial pixel neighborhood processor and method
US4891751A (en) * 1987-03-27 1990-01-02 Floating Point Systems, Inc. Massively parallel vector processing computer
US5083267A (en) * 1987-05-01 1992-01-21 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of an instruction loop with recurrance
US5036454A (en) * 1987-05-01 1991-07-30 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of a loop with overlapped code
US5276819A (en) * 1987-05-01 1994-01-04 Hewlett-Packard Company Horizontal computer having register multiconnect for operand address generation during execution of iterations of a loop of program code
US5226128A (en) * 1987-05-01 1993-07-06 Hewlett-Packard Company Horizontal computer having register multiconnect for execution of a loop with a branch
US4933895A (en) * 1987-07-10 1990-06-12 Hughes Aircraft Company Cellular array having data dependent processing capabilities
US4908751A (en) * 1987-10-15 1990-03-13 Smith Harry F Parallel data processor
US5115510A (en) * 1987-10-20 1992-05-19 Sharp Kabushiki Kaisha Multistage data flow processor with instruction packet, fetch, storage transmission and address generation controlled by destination information
US5278781A (en) * 1987-11-12 1994-01-11 Matsushita Electric Industrial Co., Ltd. Digital signal processing system
US4975870A (en) * 1988-02-25 1990-12-04 Data General Corporation Apparatus for locking a portion of a computer memory
US4896265A (en) * 1988-03-28 1990-01-23 General Electric Company Parallel broadcasting method and apparatus
WO1989009967A1 (en) * 1988-04-08 1989-10-19 Cogent Research, Inc. Computing machine with hybrid communication architecture
US5349677A (en) * 1988-05-10 1994-09-20 Cray Research, Inc. Apparatus for calculating delay when executing vector tailgating instructions and using delay to facilitate simultaneous reading of operands from and writing of results to same vector register
US5421019A (en) * 1988-10-07 1995-05-30 Martin Marietta Corporation Parallel data processor
US4984192A (en) * 1988-12-02 1991-01-08 Ultrasystems Defense Inc. Programmable state machines connectable in a reconfiguration switching network for performing real-time data processing
US5168572A (en) * 1989-03-10 1992-12-01 The Boeing Company System for dynamic selection of globally-determined optimal data path
US5179530A (en) * 1989-11-03 1993-01-12 Zoran Corporation Architecture for integrated concurrent vector signal processor
US5410723A (en) * 1989-11-21 1995-04-25 Deutsche Itt Industries Gmbh Wavefront array processor for blocking the issuance of first handshake signal (req) by the presence of second handshake signal (ack) which indicates the readyness of the receiving cell
US5121502A (en) * 1989-12-20 1992-06-09 Hewlett-Packard Company System for selectively communicating instructions from memory locations simultaneously or from the same memory locations sequentially to plurality of processing
US5197130A (en) * 1989-12-29 1993-03-23 Supercomputer Systems Limited Partnership Cluster architecture for a highly parallel scalar/vector multiprocessor system
US5561784A (en) * 1989-12-29 1996-10-01 Cray Research, Inc. Interleaved memory access system having variable-sized segments logical address spaces and means for dividing/mapping physical address into higher and lower order addresses
US5600799A (en) * 1990-04-27 1997-02-04 National Semiconductor Corporation Status batching and filtering in a media access control/host system interface unit
US5193202A (en) * 1990-05-29 1993-03-09 Wavetracer, Inc. Processor array with relocated operand physical address generator capable of data transfer to distant physical processor for each virtual processor while simulating dimensionally larger array processor
WO1991019269A1 (en) * 1990-05-29 1991-12-12 Wavetracer, Inc. Multi-dimensional processor system and processor array with massively parallel input/output
US5157785A (en) * 1990-05-29 1992-10-20 Wavetracer, Inc. Process cell for an n-dimensional processor array having a single input element with 2n data inputs, memory, and full function arithmetic logic unit
US5133073A (en) * 1990-05-29 1992-07-21 Wavetracer, Inc. Processor array of N-dimensions which is physically reconfigurable into N-1
WO1991019256A1 (en) * 1990-05-30 1991-12-12 Adaptive Solutions, Inc. Mechanism providing concurrent computational/communications in simd architecture
US5206952A (en) * 1990-09-12 1993-04-27 Cray Research, Inc. Fault tolerant networking architecture
US5717944A (en) * 1990-11-13 1998-02-10 International Business Machines Corporation Autonomous SIMD/MIMD processor memory elements
US5842031A (en) * 1990-11-13 1998-11-24 International Business Machines Corporation Advanced parallel array processor (APAP)
US6094715A (en) * 1990-11-13 2000-07-25 International Business Machine Corporation SIMD/MIMD processing synchronization
US5966528A (en) * 1990-11-13 1999-10-12 International Business Machines Corporation SIMD/MIMD array processor with vector processing
US5963746A (en) * 1990-11-13 1999-10-05 International Business Machines Corporation Fully distributed processing memory element
US5963745A (en) * 1990-11-13 1999-10-05 International Business Machines Corporation APAP I/O programmable router
US5878241A (en) * 1990-11-13 1999-03-02 International Business Machine Partitioning of processing elements in a SIMD/MIMD array processor
US5828894A (en) * 1990-11-13 1998-10-27 International Business Machines Corporation Array processor having grouping of SIMD pickets
US5588152A (en) * 1990-11-13 1996-12-24 International Business Machines Corporation Advanced parallel processor including advanced support hardware
US5822608A (en) * 1990-11-13 1998-10-13 International Business Machines Corporation Associative parallel processing system
US5815723A (en) * 1990-11-13 1998-09-29 International Business Machines Corporation Picket autonomy on a SIMD machine
US5617577A (en) * 1990-11-13 1997-04-01 International Business Machines Corporation Advanced parallel array processor I/O connection
US5809292A (en) * 1990-11-13 1998-09-15 International Business Machines Corporation Floating point for simid array machine
US5625836A (en) * 1990-11-13 1997-04-29 International Business Machines Corporation SIMD/MIMD processing memory element (PME)
US5794059A (en) * 1990-11-13 1998-08-11 International Business Machines Corporation N-dimensional modified hypercube
US5630162A (en) * 1990-11-13 1997-05-13 International Business Machines Corporation Array processor dotted communication network based on H-DOTs
US5765015A (en) * 1990-11-13 1998-06-09 International Business Machines Corporation Slide network for an array processor
US5765012A (en) * 1990-11-13 1998-06-09 International Business Machines Corporation Controller for a SIMD/MIMD array having an instruction sequencer utilizing a canned routine library
US5708836A (en) * 1990-11-13 1998-01-13 International Business Machines Corporation SIMD/MIMD inter-processor communication
US5761523A (en) * 1990-11-13 1998-06-02 International Business Machines Corporation Parallel processing system having asynchronous SIMD processing and data parallel coding
US5710935A (en) * 1990-11-13 1998-01-20 International Business Machines Corporation Advanced parallel array processor (APAP)
US5713037A (en) * 1990-11-13 1998-01-27 International Business Machines Corporation Slide bus communication functions for SIMD/MIMD array processor
US5754871A (en) * 1990-11-13 1998-05-19 International Business Machines Corporation Parallel processing system having asynchronous SIMD processing
US5717943A (en) * 1990-11-13 1998-02-10 International Business Machines Corporation Advanced parallel array processor (APAP)
US5734921A (en) * 1990-11-13 1998-03-31 International Business Machines Corporation Advanced parallel array processor computer package
US5752067A (en) * 1990-11-13 1998-05-12 International Business Machines Corporation Fully scalable parallel processing system having asynchronous SIMD processing
US5175858A (en) * 1991-03-04 1992-12-29 Adaptive Solutions, Inc. Mechanism providing concurrent computational/communications in SIMD architecture
US5241492A (en) * 1991-05-06 1993-08-31 Motorola, Inc. Apparatus for performing multiply and accumulate instructions with reduced power and a method therefor
US5594918A (en) * 1991-05-13 1997-01-14 International Business Machines Corporation Parallel computer system providing multi-ported intelligent memory
US5623689A (en) * 1991-07-16 1997-04-22 Matsushita Electric Industrial Co., Ltd. Parallel processor system for quickly detecting the termination of data transmission
US5701509A (en) * 1991-07-16 1997-12-23 Matsushita Electric Industrial Co., Ltd. Parallel processor system
US6597362B1 (en) 1991-12-06 2003-07-22 Hyperchip Inc. Integrated circuit having lithographical cell array interconnections
US5801715A (en) * 1991-12-06 1998-09-01 Norman; Richard S. Massively-parallel processor array with outputs from individual processors directly to an external device without involving other processors or a common physical carrier
US5465375A (en) * 1992-01-14 1995-11-07 France Telecom Multiprocessor system with cascaded modules combining processors through a programmable logic cell array
US5506992A (en) * 1992-01-30 1996-04-09 Saxenmeyer; George Distributed processing system with asynchronous communication between processing modules
US6104439A (en) * 1992-02-08 2000-08-15 Samsung Electronics Co., Ltd. Method and apparatus for motion estimation
US5489949A (en) * 1992-02-08 1996-02-06 Samsung Electronics Co., Ltd. Method and apparatus for motion estimation
US5991866A (en) * 1992-03-25 1999-11-23 Tm Patents, Lp Method and system for generating a program to facilitate rearrangement of address bits among addresses in a massively parallel processor system
US5805915A (en) * 1992-05-22 1998-09-08 International Business Machines Corporation SIMIMD array processing system
US5428803A (en) * 1992-07-10 1995-06-27 Cray Research, Inc. Method and apparatus for a unified parallel processing architecture
US5625831A (en) * 1992-07-10 1997-04-29 Cray Research, Inc. Extendible clock mechanism
US5555386A (en) * 1992-11-26 1996-09-10 Sharp Kabushiki Kaisha Data flow processor with variable logic connection between processors in a system
US5581767A (en) * 1993-06-16 1996-12-03 Nippon Sheet Glass Co., Ltd. Bus structure for multiprocessor system having separated processor section and control/memory section
US6507217B2 (en) 1993-08-03 2003-01-14 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US20040088672A1 (en) * 1993-08-03 2004-05-06 Ting Benjamin S. Architecture and interconnect scheme for programmable logic circuits
US6747482B2 (en) 1993-08-03 2004-06-08 Btr. Inc. Architecture and interconnect scheme for programmable logic circuits
US6597196B2 (en) 1993-08-03 2003-07-22 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US8289047B2 (en) 1993-08-03 2012-10-16 Actel Corporation Architecture and interconnect scheme for programmable logic circuits
US20080265938A1 (en) * 1993-08-03 2008-10-30 Ting Benjamin S Architecture and interconnect scheme for programmable logic circuits
US7409664B2 (en) 1993-08-03 2008-08-05 Actel Corporation Architecture and interconnect scheme for programmable logic circuits
US20110050282A1 (en) * 1993-08-03 2011-03-03 Ting Benjamin S Architecture and interconnect scheme for programmable logic circuits
US6989688B2 (en) 1993-08-03 2006-01-24 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US7017136B2 (en) 1993-08-03 2006-03-21 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US6703861B2 (en) 1993-08-03 2004-03-09 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US7646218B2 (en) 1993-08-03 2010-01-12 Actel Corporation Architecture and interconnect scheme for programmable logic circuits
US20100073024A1 (en) * 1993-08-03 2010-03-25 Ting Benjamin S Architecture and interconnect scheme for programmable logic circuits
US7142012B2 (en) 1993-08-03 2006-11-28 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US20060076974A1 (en) * 1993-08-03 2006-04-13 Ting Benjamin S Architecture and interconnect scheme for programmable logic circuits
US6462578B2 (en) 1993-08-03 2002-10-08 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US20060202717A1 (en) * 1993-08-03 2006-09-14 Ting Benjamin S Architecture and interconnect scheme for programmable logic circuits
US7078933B2 (en) 1993-08-03 2006-07-18 Btr, Inc. Architecture and interconnect scheme for programmable logic circuits
US20060095886A1 (en) * 1993-08-03 2006-05-04 Ting Beniamin S Architecture and interconnect scheme for programmable logic circuits
US6073185A (en) * 1993-08-27 2000-06-06 Teranex, Inc. Parallel data processor
US5485576A (en) * 1994-01-28 1996-01-16 Fee; Brendan Chassis fault tolerant system management bus architecture for a networking
US5754596A (en) * 1994-02-23 1998-05-19 Rosemount Inc. Field transmitter for storing information
US6145071A (en) * 1994-03-03 2000-11-07 The George Washington University Multi-layer multi-processor information conveyor with periodic transferring of processors' states for on-the-fly transformation of continuous information flows and operating method therefor
US5748872A (en) * 1994-03-22 1998-05-05 Norman; Richard S. Direct replacement cell fault tolerant architecture
US6038682A (en) * 1994-03-22 2000-03-14 Hyperchip Inc. Fault tolerant data processing system fabricated on a monolithic substrate
US6636986B2 (en) 1994-03-22 2003-10-21 Hyperchip Inc. Output and/or input coordinated processing array
US5708847A (en) * 1994-05-19 1998-01-13 Yamaha Corporation Method of digital signal processing and apparatus using a reference operation cycle including a processing period and a transfer period
US5689450A (en) * 1994-08-30 1997-11-18 Sony Corporation Parallel processor
US7126375B2 (en) 1995-05-03 2006-10-24 Btr, Inc. Floor plan for scalable multiple level tab oriented interconnect architecture
US7009422B2 (en) 1995-05-03 2006-03-07 Btr, Inc. Floor plan for scalable multiple level tab oriented interconnect architecture
US20060114023A1 (en) * 1995-05-03 2006-06-01 Ting Benjamin S Floor plan for scalable multiple level tab oriented interconnect architecture
US6300793B1 (en) 1995-05-03 2001-10-09 Btr, Inc. Scalable multiple level tab oriented interconnect architecture
US20020070756A1 (en) * 1995-05-03 2002-06-13 Ting Benjamins S. Floor plan for scalable multiple level tab oriented interconnect architecture
US6417690B1 (en) * 1995-05-03 2002-07-09 Btr, Inc. Floor plan for scalable multiple level tab oriented interconnect architecture
US6859869B1 (en) * 1995-11-17 2005-02-22 Pact Xpp Technologies Ag Data processing system
US6003098A (en) * 1996-04-30 1999-12-14 Hewlett-Packard Company Graphic accelerator architecture using two graphics processing units for processing aspects of pre-rasterized graphics primitives and a control circuitry for relaying pass-through information
US5949440A (en) * 1996-04-30 1999-09-07 Hewlett Packard Compnay Method and apparatus for processing graphics primitives in multiple modes using reconfigurable hardware
US7915918B2 (en) 1996-09-04 2011-03-29 Actel Corporation Method and apparatus for universal program controlled bus architecture
US20040178822A1 (en) * 1996-09-04 2004-09-16 Pani Peter M. Method and apparatus for universal program controlled bus architecture
US20080191739A1 (en) * 1996-09-04 2008-08-14 Pani Peter M Method and apparatus for universal program controlled bus architecture
US6504399B2 (en) 1996-09-04 2003-01-07 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US20110043248A1 (en) * 1996-09-04 2011-02-24 Pani Peter M Method and apparatus for universal program controlled bus architecture
US6975138B2 (en) 1996-09-04 2005-12-13 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US6329839B1 (en) 1996-09-04 2001-12-11 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US20060202716A1 (en) * 1996-09-04 2006-09-14 Pani Peter M Method and apparatus for universal program controlled bus architecture
US7382156B2 (en) 1996-09-04 2008-06-03 Actel Corporation Method and apparatus for universal program controlled bus architecture
US7830173B2 (en) 1996-09-04 2010-11-09 Actel Corporation Method and apparatus for universal program controlled bus architecture
US8156312B2 (en) 1996-12-09 2012-04-10 Martin Vorbach Processor chip for reconfigurable data processing, for processing numeric and logic operations and including function and interconnection control units
US20040168099A1 (en) * 1996-12-09 2004-08-26 Martin Vorbach Unit for processing numeric and logic operations for use in central processing units (CPUs), multiprocessor systems
US7822968B2 (en) 1996-12-09 2010-10-26 Martin Vorbach Circuit having a multidimensional structure of configurable cells that include multi-bit-wide inputs and outputs
US20090146690A1 (en) * 1996-12-09 2009-06-11 Martin Vorbach Runtime configurable arithmetic and logic cell
US20030056085A1 (en) * 1996-12-09 2003-03-20 Entire Interest Unit for processing numeric and logic operations for use in central processing units (CPUS), multiprocessor systems, data-flow processors (DSPS), systolic processors and field programmable gate arrays (FPGAS)
US20080010437A1 (en) * 1996-12-09 2008-01-10 Martin Vorbach Unit for processing numeric and logic operations for use in central processing units (CPUS), multiprocessor systems, data-flow processors (DSPS), systolic processors and field programmable gate arrays (FPGAS)
US7237087B2 (en) 1996-12-09 2007-06-26 Pact Xpp Technologies Ag Reconfigurable multidimensional array processor allowing runtime reconfiguration of selected individual array cells
US20110010523A1 (en) * 1996-12-09 2011-01-13 Martin Vorbach Runtime configurable arithmetic and logic cell
US7565525B2 (en) 1996-12-09 2009-07-21 Pact Xpp Technologies Ag Runtime configurable arithmetic and logic cell
US7650448B2 (en) 1996-12-20 2010-01-19 Pact Xpp Technologies Ag I/O and memory bus system for DFPS and units with two- or multi-dimensional programmable cell architectures
US8195856B2 (en) 1996-12-20 2012-06-05 Martin Vorbach I/O and memory bus system for DFPS and units with two- or multi-dimensional programmable cell architectures
US20100287318A1 (en) * 1996-12-20 2010-11-11 Martin Vorbach I/o and memory bus system for dfps and units with two- or multi-dimensional programmable cell architectures
US7174443B1 (en) 1996-12-20 2007-02-06 Pact Xpp Technologies Ag Run-time reconfiguration method for programmable units
US7899962B2 (en) 1996-12-20 2011-03-01 Martin Vorbach I/O and memory bus system for DFPs and units with two- or multi-dimensional programmable cell architectures
US20080222329A1 (en) * 1996-12-20 2008-09-11 Martin Vorbach I/O and memory bus system for DFPs and units with two- or multi-dimensional programmable cell architectures
US20100082863A1 (en) * 1996-12-20 2010-04-01 Martin Vorbach I/O AND MEMORY BUS SYSTEM FOR DFPs AND UNITS WITH TWO- OR MULTI-DIMENSIONAL PROGRAMMABLE CELL ARCHITECTURES
US7028107B2 (en) 1996-12-27 2006-04-11 Pact Xpp Technologies Ag Process for automatic dynamic reloading of data flow processors (DFPS) and units with two- or three- dimensional programmable cell architectures (FPGAS, DPGAS, and the like)
US20030093662A1 (en) * 1996-12-27 2003-05-15 Pact Gmbh Process for automatic dynamic reloading of data flow processors (DFPS) and units with two- or three-dimensional programmable cell architectures (FPGAS, DPGAS, and the like)
US20090153188A1 (en) * 1996-12-27 2009-06-18 Martin Vorbach PROCESS FOR AUTOMATIC DYNAMIC RELOADING OF DATA FLOW PROCESSORS (DFPs) AND UNITS WITH TWO- OR THREE-DIMENSIONAL PROGRAMMABLE CELL ARCHITECTURES (FPGAs, DPGAs AND THE LIKE)
US20090144485A1 (en) * 1996-12-27 2009-06-04 Martin Vorbach Process for automatic dynamic reloading of data flow processors (dfps) and units with two- or three-dimensional programmable cell architectures (fpgas, dpgas, and the like)
US20060031595A1 (en) * 1996-12-27 2006-02-09 Martin Vorbach Process for automatic dynamic reloading of data flow processors (DFPs) and units with two- or three-dimensional programmable cell architectures (FPGAs, DPGAs, and the like
US7822881B2 (en) 1996-12-27 2010-10-26 Martin Vorbach Process for automatic dynamic reloading of data flow processors (DFPs) and units with two- or three-dimensional programmable cell architectures (FPGAs, DPGAs, and the like)
USRE44383E1 (en) 1997-02-08 2013-07-16 Martin Vorbach Method of self-synchronization of configurable elements of a programmable module
US7036036B2 (en) 1997-02-08 2006-04-25 Pact Xpp Technologies Ag Method of self-synchronization of configurable elements of a programmable module
US6968452B2 (en) 1997-02-08 2005-11-22 Pact Xpp Technologies Ag Method of self-synchronization of configurable elements of a programmable unit
USRE44365E1 (en) 1997-02-08 2013-07-09 Martin Vorbach Method of self-synchronization of configurable elements of a programmable module
USRE45223E1 (en) 1997-02-08 2014-10-28 Pact Xpp Technologies Ag Method of self-synchronization of configurable elements of a programmable module
USRE45109E1 (en) 1997-02-08 2014-09-02 Pact Xpp Technologies Ag Method of self-synchronization of configurable elements of a programmable module
US20040083399A1 (en) * 1997-02-08 2004-04-29 Martin Vorbach Method of self-synchronization of configurable elements of a programmable module
US20040052130A1 (en) * 1997-02-08 2004-03-18 Martin Vorbach Method of self-synchronization of configurable elements of a programmable unit
US7010667B2 (en) * 1997-02-11 2006-03-07 Pact Xpp Technologies Ag Internal bus system for DFPS and units with two- or multi-dimensional programmable cell architectures, for managing large volumes of data with a high interconnection complexity
US20030135686A1 (en) * 1997-02-11 2003-07-17 Martin Vorbach Internal bus system for DFPs and units with two- or multi-dimensional programmable cell architectures, for managing large volumes of data with a high interconnection complexity
US6502180B1 (en) * 1997-09-12 2002-12-31 California Institute Of Technology Asynchronous circuits with pipelined completion process
US20030140214A1 (en) * 1997-09-12 2003-07-24 California Institute Of Technology Pipelined completion for asynchronous communication
US20090300445A1 (en) * 1997-12-22 2009-12-03 Martin Vorbach Method and system for alternating between programs for execution by cells of an integrated circuit
US20040181726A1 (en) * 1997-12-22 2004-09-16 Martin Vorbach Method and system for alternating between programs for execution by cells of an integrated circuit
US8819505B2 (en) 1997-12-22 2014-08-26 Pact Xpp Technologies Ag Data processor having disabled cores
US6185667B1 (en) 1998-04-09 2001-02-06 Teranex, Inc. Input/output support for processing in a mesh connected computer
US6067609A (en) * 1998-04-09 2000-05-23 Teranex, Inc. Pattern generation and shift plane operations for a mesh connected computer
US6275920B1 (en) 1998-04-09 2001-08-14 Teranex, Inc. Mesh connected computed
US6212628B1 (en) 1998-04-09 2001-04-03 Teranex, Inc. Mesh connected computer
US6173388B1 (en) 1998-04-09 2001-01-09 Teranex Inc. Directly accessing local memories of array processors for improved real-time corner turning processing
US6421772B1 (en) * 1998-06-04 2002-07-16 Kabushiki Kaisha Toshiba Parallel computer with improved access to adjacent processor and memory elements
US20020152366A1 (en) * 1998-06-04 2002-10-17 Kabushi Kaisha Toshiba Parallel computer with improved access to adjacent processor and memory elements
US6968442B2 (en) * 1998-06-04 2005-11-22 Kabushiki Kaisha Toshiba Parallel computer with improved access to adjacent processor and memory elements
US6624658B2 (en) 1999-02-04 2003-09-23 Advantage Logic, Inc. Method and apparatus for universal program controlled bus architecture
US8468329B2 (en) 1999-02-25 2013-06-18 Martin Vorbach Pipeline configuration protocol and configuration unit communication
US7784093B2 (en) 1999-04-01 2010-08-24 Juniper Networks, Inc. Firewall including local bus
US8490158B2 (en) 1999-04-01 2013-07-16 Juniper Networks, Inc. Firewall including local bus
US7823195B1 (en) * 1999-04-01 2010-10-26 Juniper Networks, Inc. Method, apparatus and computer program product for a network firewall
US6701432B1 (en) * 1999-04-01 2004-03-02 Netscreen Technologies, Inc. Firewall including local bus
US20100281532A1 (en) * 1999-04-01 2010-11-04 Juniper Networks, Inc. Firewall including local bus
US20080209540A1 (en) * 1999-04-01 2008-08-28 Juniper Networks, Inc. Firewall including local bus
US20040158744A1 (en) * 1999-04-01 2004-08-12 Netscreen Technologies, Inc., A Delaware Corporation Firewall including local bus
US7363653B2 (en) 1999-04-01 2008-04-22 Juniper Networks, Inc. Firewall including local bus
US8230411B1 (en) 1999-06-10 2012-07-24 Martin Vorbach Method for interleaving a program over a plurality of cells
US20100228918A1 (en) * 1999-06-10 2010-09-09 Martin Vorbach Configurable logic integrated circuit having a multidimensional structure of configurable elements
US8312200B2 (en) 1999-06-10 2012-11-13 Martin Vorbach Processor chip including a plurality of cache elements connected to a plurality of processor cores
US20110012640A1 (en) * 1999-06-10 2011-01-20 Martin Vorbach Configurable logic integrated circuit having a multidimensional structure of configurable elements
US8726250B2 (en) 1999-06-10 2014-05-13 Pact Xpp Technologies Ag Configurable logic integrated circuit having a multidimensional structure of configurable elements
US6487651B1 (en) 1999-10-26 2002-11-26 Assabet Ventures MIMD arrangement of SIMD machines
US6356993B1 (en) 1999-10-26 2002-03-12 Pyxsys Corporation Dual aspect ratio PE array with no connection switching
US6728863B1 (en) 1999-10-26 2004-04-27 Assabet Ventures Wide connections for transferring data between PE's of an N-dimensional mesh-connected SIMD array while transferring operands from memory
WO2001031473A1 (en) * 1999-10-26 2001-05-03 Arthur D. Little, Inc. Multiplexing n-dimensional mesh connections onto (n + 1) data paths
US6320412B1 (en) 1999-12-20 2001-11-20 Btr, Inc. C/O Corporate Trust Co. Architecture and interconnect for programmable logic circuits
US7003660B2 (en) 2000-06-13 2006-02-21 Pact Xpp Technologies Ag Pipeline configuration unit protocols and communication
US20050223212A1 (en) * 2000-06-13 2005-10-06 Martin Vorbach Pipeline configuration protocol and configuration unit communication
US8301872B2 (en) 2000-06-13 2012-10-30 Martin Vorbach Pipeline configuration protocol and configuration unit communication
US20070136560A1 (en) * 2000-08-22 2007-06-14 Graham Kirsch Method and apparatus for a shift register based interconnection for a massively parallel processor array
US7409529B2 (en) 2000-08-22 2008-08-05 Micron Technology, Inc. Method and apparatus for a shift register based interconnection for a massively parallel processor array
US20040250047A1 (en) * 2000-08-22 2004-12-09 Graham Kirsch Method and apparatus for a shift register based interconnection for a massively parallel processor array
US7149876B2 (en) * 2000-08-22 2006-12-12 Micron Technology, Inc. Method and apparatus for a shift register based interconnection for a massively parallel processor array
US6754801B1 (en) * 2000-08-22 2004-06-22 Micron Technology, Inc. Method and apparatus for a shift register based interconnection for a massively parallel processor array
US20040015899A1 (en) * 2000-10-06 2004-01-22 Frank May Method for processing data
US20090146691A1 (en) * 2000-10-06 2009-06-11 Martin Vorbach Logic cell array and bus system
US9047440B2 (en) 2000-10-06 2015-06-02 Pact Xpp Technologies Ag Logical cell array and bus system
US8058899B2 (en) 2000-10-06 2011-11-15 Martin Vorbach Logic cell array and bus system
US8471593B2 (en) 2000-10-06 2013-06-25 Martin Vorbach Logic cell array and bus system
US7595659B2 (en) 2000-10-09 2009-09-29 Pact Xpp Technologies Ag Logic cell array and bus system
US8904148B2 (en) 2000-12-19 2014-12-02 Intel Corporation Processor architecture with switch matrices for transferring data along buses
US6990555B2 (en) 2001-01-09 2006-01-24 Pact Xpp Technologies Ag Method of hierarchical caching of configuration data having dataflow processors and modules having two- or multidimensional programmable cell structure (FPGAs, DPGAs, etc.)
US20090300262A1 (en) * 2001-03-05 2009-12-03 Martin Vorbach Methods and devices for treating and/or processing data
US20090210653A1 (en) * 2001-03-05 2009-08-20 Pact Xpp Technologies Ag Method and device for treating and processing data
US20070113046A1 (en) * 2001-03-05 2007-05-17 Martin Vorbach Data processing device and method
US20110060942A1 (en) * 2001-03-05 2011-03-10 Martin Vorbach Methods and devices for treating and/or processing data
US7844796B2 (en) 2001-03-05 2010-11-30 Martin Vorbach Data processing device and method
US8145881B2 (en) 2001-03-05 2012-03-27 Martin Vorbach Data processing device and method
US7444531B2 (en) 2001-03-05 2008-10-28 Pact Xpp Technologies Ag Methods and devices for treating and processing data
US20090100286A1 (en) * 2001-03-05 2009-04-16 Martin Vorbach Methods and devices for treating and processing data
US20090144522A1 (en) * 2001-03-05 2009-06-04 Martin Vorbach Data Processing Device and Method
US20110173389A1 (en) * 2001-03-05 2011-07-14 Martin Vorbach Methods and devices for treating and/or processing data
US9037807B2 (en) 2001-03-05 2015-05-19 Pact Xpp Technologies Ag Processor arrangement on a chip including data processing, memory, and interface elements
US9075605B2 (en) 2001-03-05 2015-07-07 Pact Xpp Technologies Ag Methods and devices for treating and processing data
US7581076B2 (en) 2001-03-05 2009-08-25 Pact Xpp Technologies Ag Methods and devices for treating and/or processing data
US8099618B2 (en) 2001-03-05 2012-01-17 Martin Vorbach Methods and devices for treating and processing data
US20100023796A1 (en) * 2001-03-05 2010-01-28 Martin Vorbach Methods and devices for treating and processing data
US20050066213A1 (en) * 2001-03-05 2005-03-24 Martin Vorbach Methods and devices for treating and processing data
US8312301B2 (en) 2001-03-05 2012-11-13 Martin Vorbach Methods and devices for treating and processing data
US7657877B2 (en) 2001-06-20 2010-02-02 Pact Xpp Technologies Ag Method for processing data
US20100095094A1 (en) * 2001-06-20 2010-04-15 Martin Vorbach Method for processing data
US20040243984A1 (en) * 2001-06-20 2004-12-02 Martin Vorbach Data processing method
US7210129B2 (en) 2001-08-16 2007-04-24 Pact Xpp Technologies Ag Method for translating programs for reconfigurable architectures
US7996827B2 (en) 2001-08-16 2011-08-09 Martin Vorbach Method for the translation of programs for reconfigurable architectures
US8869121B2 (en) 2001-08-16 2014-10-21 Pact Xpp Technologies Ag Method for the translation of programs for reconfigurable architectures
US7480825B2 (en) 2001-09-03 2009-01-20 Pact Xpp Technologies Ag Method for debugging reconfigurable architectures
US8069373B2 (en) 2001-09-03 2011-11-29 Martin Vorbach Method for debugging reconfigurable architectures
US8209653B2 (en) 2001-09-03 2012-06-26 Martin Vorbach Router
US20060245225A1 (en) * 2001-09-03 2006-11-02 Martin Vorbach Reconfigurable elements
US7840842B2 (en) 2001-09-03 2010-11-23 Martin Vorbach Method for debugging reconfigurable architectures
US20030046607A1 (en) * 2001-09-03 2003-03-06 Frank May Method for debugging reconfigurable architectures
US20050053056A1 (en) * 2001-09-03 2005-03-10 Martin Vorbach Router
US7266725B2 (en) 2001-09-03 2007-09-04 Pact Xpp Technologies Ag Method for debugging reconfigurable architectures
US20050022062A1 (en) * 2001-09-03 2005-01-27 Martin Vorbach Method for debugging reconfigurable architectures
US20090150725A1 (en) * 2001-09-03 2009-06-11 Martin Vorbach Method for debugging reconfigurable architectures
US8407525B2 (en) 2001-09-03 2013-03-26 Pact Xpp Technologies Ag Method for debugging reconfigurable architectures
US7434191B2 (en) 2001-09-03 2008-10-07 Pact Xpp Technologies Ag Router
US8429385B2 (en) 2001-09-03 2013-04-23 Martin Vorbach Device including a field having function cells and information providing cells controlled by the function cells
US8686549B2 (en) 2001-09-03 2014-04-01 Martin Vorbach Reconfigurable elements
US20090037865A1 (en) * 2001-09-03 2009-02-05 Martin Vorbach Router
US8686475B2 (en) 2001-09-19 2014-04-01 Pact Xpp Technologies Ag Reconfigurable elements
US20040249880A1 (en) * 2001-12-14 2004-12-09 Martin Vorbach Reconfigurable system
US7577822B2 (en) 2001-12-14 2009-08-18 Pact Xpp Technologies Ag Parallel task operation in processor and reconfigurable coprocessor configured based on information in link list including termination information for synchronization
US20050132344A1 (en) * 2002-01-18 2005-06-16 Martin Vorbach Method of compilation
US20060090062A1 (en) * 2002-01-19 2006-04-27 Martin Vorbach Reconfigurable processor
US8281108B2 (en) 2002-01-19 2012-10-02 Martin Vorbach Reconfigurable general purpose processor having time restricted configurations
US8127061B2 (en) 2002-02-18 2012-02-28 Martin Vorbach Bus systems and reconfiguration methods
US20100174868A1 (en) * 2002-03-21 2010-07-08 Martin Vorbach Processor device having a sequential data processing unit and an arrangement of data processing elements
US20060075211A1 (en) * 2002-03-21 2006-04-06 Martin Vorbach Method and device for data processing
US7987339B2 (en) 2002-06-26 2011-07-26 Coherent Logix, Incorporated Processing system with interspersed processors and dynamic pathway creation
US20040030859A1 (en) * 2002-06-26 2004-02-12 Doerr Michael B. Processing system with interspersed processors and communication elements
US20100268914A1 (en) * 2002-06-26 2010-10-21 Doerr Michael B Processing system with interspersed processors and dynamic pathway creation
US8832413B2 (en) 2002-06-26 2014-09-09 Coherent Logix, Incorporated Processing system with interspersed processors and communication elements having improved wormhole routing
US7937558B2 (en) 2002-06-26 2011-05-03 Coherent Logix, Incorporated Processing system with interspersed processors and communication elements
US8478964B2 (en) 2002-06-26 2013-07-02 Coherent Logix, Incorporated Stall propagation in a processing system with interspersed processors and communicaton elements
US7415594B2 (en) 2002-06-26 2008-08-19 Coherent Logix, Incorporated Processing system with interspersed stall propagating processors and communication elements
US9535877B2 (en) 2002-06-26 2017-01-03 Coherent Logix, Incorporated Processing system with interspersed processors and communication elements having improved communication routing
US20100153654A1 (en) * 2002-08-07 2010-06-17 Martin Vorbach Data processing method and device
US20060248317A1 (en) * 2002-08-07 2006-11-02 Martin Vorbach Method and device for processing data
US8281265B2 (en) 2002-08-07 2012-10-02 Martin Vorbach Method and device for processing data
US8156284B2 (en) 2002-08-07 2012-04-10 Martin Vorbach Data processing method and device
US8914590B2 (en) 2002-08-07 2014-12-16 Pact Xpp Technologies Ag Data processing method and device
US7657861B2 (en) 2002-08-07 2010-02-02 Pact Xpp Technologies Ag Method and device for processing data
US20070050603A1 (en) * 2002-08-07 2007-03-01 Martin Vorbach Data processing method and device
US20100070671A1 (en) * 2002-08-07 2010-03-18 Martin Vorbach Method and device for processing data
US20110238948A1 (en) * 2002-08-07 2011-09-29 Martin Vorbach Method and device for coupling a data processing unit and a data processing array
US7394284B2 (en) 2002-09-06 2008-07-01 Pact Xpp Technologies Ag Reconfigurable sequencer structure
US20110006805A1 (en) * 2002-09-06 2011-01-13 Martin Vorbach Reconfigurable sequencer structure
US7602214B2 (en) 2002-09-06 2009-10-13 Pact Xpp Technologies Ag Reconfigurable sequencer structure
US7928763B2 (en) 2002-09-06 2011-04-19 Martin Vorbach Multi-core processing system
US7782087B2 (en) 2002-09-06 2010-08-24 Martin Vorbach Reconfigurable sequencer structure
US20110148460A1 (en) * 2002-09-06 2011-06-23 Martin Vorbach Reconfigurable sequencer structure
US20060192586A1 (en) * 2002-09-06 2006-08-31 Martin Vorbach Reconfigurable sequencer structure
US8310274B2 (en) 2002-09-06 2012-11-13 Martin Vorbach Reconfigurable sequencer structure
US20080191737A1 (en) * 2002-09-06 2008-08-14 Martin Vorbach Reconfigurable sequencer structure
US8803552B2 (en) 2002-09-06 2014-08-12 Pact Xpp Technologies Ag Reconfigurable sequencer structure
US7574582B2 (en) * 2003-01-27 2009-08-11 Picochip Designs Limited Processor array including delay elements associated with primary bus nodes
US20060155956A1 (en) * 2003-01-27 2006-07-13 Nolan John M Processor array
US7516300B2 (en) * 2003-03-31 2009-04-07 Micron Technology, Inc. Active memory processing array topography and method
US20070033379A1 (en) * 2003-03-31 2007-02-08 Graham Kirsch Active memory processing array topography and method
US20070011433A1 (en) * 2003-04-04 2007-01-11 Martin Vorbach Method and device for data processing
US7457234B1 (en) 2003-05-14 2008-11-25 Adtran, Inc. System and method for protecting communication between a central office and a remote premises
US20040255096A1 (en) * 2003-06-11 2004-12-16 Norman Richard S. Method for continuous linear production of integrated circuits
US20070083730A1 (en) * 2003-06-17 2007-04-12 Martin Vorbach Data processing device and method
US20090172351A1 (en) * 2003-08-28 2009-07-02 Martin Vorbach Data processing device and method
US20100241823A1 (en) * 2003-08-28 2010-09-23 Martin Vorbach Data processing device and method
US8812820B2 (en) * 2003-08-28 2014-08-19 Pact Xpp Technologies Ag Data processing device and method
US9021236B2 (en) * 2003-09-08 2015-04-28 Altera Corporation Methods and apparatus for storing expanded width instructions in a VLIW memory for deferred execution
US20140173253A1 (en) * 2003-09-08 2014-06-19 Altera Corporation Methods and Apparatus for Storing Expanded Width Instructions in a VLIW Memory for Deferred Execution
US20080278678A1 (en) * 2003-10-09 2008-11-13 Howell Thomas A Eyeglasses with user monitoring
US7557613B2 (en) 2004-03-30 2009-07-07 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US7768302B2 (en) 2004-03-30 2010-08-03 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US20050218928A1 (en) * 2004-03-30 2005-10-06 Pani Peter M Scalable non-blocking switching network for programmable logic
US6975139B2 (en) 2004-03-30 2005-12-13 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US7256614B2 (en) 2004-03-30 2007-08-14 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US20100244895A1 (en) * 2004-03-30 2010-09-30 Pani Peter M Scalable non-blocking switching network for programmable logic
US20090273368A1 (en) * 2004-03-30 2009-11-05 Pani Peter M Scalable non-blocking switching network for programmable logic
US7417457B2 (en) 2004-03-30 2008-08-26 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US7986163B2 (en) 2004-03-30 2011-07-26 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US20110089972A1 (en) * 2004-03-30 2011-04-21 Pani Peter M Scalable non-blocking switching network for programmable logic
US20060006906A1 (en) * 2004-03-30 2006-01-12 Pani Peter M Scalable non-blocking switching network for programmable logic
US8242807B2 (en) 2004-03-30 2012-08-14 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US8698519B2 (en) 2004-03-30 2014-04-15 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US20080272806A1 (en) * 2004-03-30 2008-11-06 Pani Peter M Scalable non-blocking switching network for programmable logic
US7863932B2 (en) 2004-03-30 2011-01-04 Advantage Logic, Inc. Scalable non-blocking switching network for programmable logic
US20070268041A1 (en) * 2004-03-30 2007-11-22 Pani Peter M Scalable non-blocking switching network for programmable logic
US20060023704A1 (en) * 2004-07-29 2006-02-02 Pani Peter M Interconnection fabric using switching networks in hierarchy
US7460529B2 (en) 2004-07-29 2008-12-02 Advantage Logic, Inc. Interconnection fabric using switching networks in hierarchy
US20060031659A1 (en) * 2004-08-09 2006-02-09 Arches Computing Systems Multi-processor reconfigurable computing system
US7779177B2 (en) 2004-08-09 2010-08-17 Arches Computing Systems Multi-processor reconfigurable computing system
US20090031104A1 (en) * 2005-02-07 2009-01-29 Martin Vorbach Low Latency Massive Parallel Data Processing Device
US8560795B2 (en) * 2005-06-30 2013-10-15 Imec Memory arrangement for multi-processor systems including a memory queue
US20080140980A1 (en) * 2005-06-30 2008-06-12 Interuniversitair Microelektronica Centrum (Imec) Vzw Memory arrangement for multi-processor systems
US20070061661A1 (en) * 2005-07-06 2007-03-15 Stmicroelectronics S.A. Bit rate adaptation in a data processing flow
US7392332B2 (en) * 2005-07-06 2008-06-24 Stmicroelectronics S.A. Bit rate adaptation in a data processing flow
US20070123091A1 (en) * 2005-11-18 2007-05-31 Swedberg Benjamin D Releasable Wire Connector
US8250503B2 (en) 2006-01-18 2012-08-21 Martin Vorbach Hardware definition method including determining whether to implement a function as hardware or software
US7423453B1 (en) 2006-01-20 2008-09-09 Advantage Logic, Inc. Efficient integrated circuit layout scheme to implement a scalable switching network used in interconnection fabric
US20070226686A1 (en) * 2006-03-27 2007-09-27 Beardslee John M Programming a multi-processor system
US8826228B2 (en) 2006-03-27 2014-09-02 Coherent Logix, Incorporated Programming a multi-processor system
US10776085B2 (en) 2006-03-27 2020-09-15 Coherent Logix, Incorporated Programming a multi-processor system
US9250867B2 (en) 2006-03-27 2016-02-02 Coherent Logix, Incorporated Programming a multi-processor system
US9965258B2 (en) 2006-03-27 2018-05-08 Coherent Logix, Incorporated Programming a multi-processor system
US20080263118A1 (en) * 2007-04-06 2008-10-23 Montvelishsky Michael B System for convolution calculation with multiple computer processors
US8559998B2 (en) 2007-11-05 2013-10-15 Mindspeed Technologies U.K., Limited Power control
US20090149211A1 (en) * 2007-11-05 2009-06-11 Picochip Designs Limited Power control
US20090158007A1 (en) * 2007-12-12 2009-06-18 Itt Manufacturing Enterprises, Inc. Scaleable array of micro-engines for waveform processing
US8078829B2 (en) * 2007-12-12 2011-12-13 Itt Manufacturing Enterprises, Inc. Scaleable array of micro-engines for waveform processing
US20090182993A1 (en) * 2007-12-13 2009-07-16 Karl Fant Concurrent processing element system, and method
US8078839B2 (en) * 2007-12-13 2011-12-13 Wave Semiconductor Concurrent processing element system, and method
US20110002426A1 (en) * 2009-01-05 2011-01-06 Picochip Designs Limited Rake Receiver
US8849340B2 (en) 2009-05-07 2014-09-30 Intel Corporation Methods and devices for reducing interference in an uplink
US8862076B2 (en) 2009-06-05 2014-10-14 Intel Corporation Method and device in a communication network
US8892154B2 (en) 2009-06-05 2014-11-18 Intel Corporation Method and device in a communication network
US8463312B2 (en) 2009-06-05 2013-06-11 Mindspeed Technologies U.K., Limited Method and device in a communication network
US9807771B2 (en) 2009-06-05 2017-10-31 Intel Corporation Method and device in a communication network
US7999570B2 (en) 2009-06-24 2011-08-16 Advantage Logic, Inc. Enhanced permutable switching network with multicasting signals for interconnection fabric
US20100327907A1 (en) * 2009-06-24 2010-12-30 Ting Benjamin S Enhanced permutable switching network with multicasting signals for interconnection fabric
US8395415B2 (en) 2009-06-24 2013-03-12 Advantage Logic, Inc. Enhanced permutable switching network with multicasting signals for interconnection fabric
US8798630B2 (en) 2009-10-05 2014-08-05 Intel Corporation Femtocell base station
US9107136B2 (en) 2010-08-16 2015-08-11 Intel Corporation Femtocell access control
US10685143B2 (en) 2010-10-15 2020-06-16 Coherent Logix, Incorporated Secure boot sequence for selectively disabling configurable communication paths of a multiprocessor fabric
US8880866B2 (en) 2010-10-15 2014-11-04 Coherent Logix, Incorporated Method and system for disabling communication paths in a multiprocessor fabric by setting register values to disable the communication paths specified by a configuration
US9424441B2 (en) 2010-10-15 2016-08-23 Coherent Logix, Incorporated Multiprocessor fabric having configurable communication that is selectively disabled for secure processing
US10007806B2 (en) 2010-10-15 2018-06-26 Coherent Logix, Incorporated Secure boot sequence for selectively disabling configurable communication paths of a multiprocessor fabric
US10856302B2 (en) 2011-04-05 2020-12-01 Intel Corporation Multimode base station
US9042434B2 (en) 2011-04-05 2015-05-26 Intel Corporation Filter
US8712469B2 (en) 2011-05-16 2014-04-29 Mindspeed Technologies U.K., Limited Accessing a base station
US10698976B2 (en) * 2017-05-17 2020-06-30 Google Llc Low latency matrix multiply unit
US20190354571A1 (en) * 2017-05-17 2019-11-21 Google Llc Low latency matrix multiply unit
US10698974B2 (en) * 2017-05-17 2020-06-30 Google Llc Low latency matrix multiply unit
US20180336163A1 (en) * 2017-05-17 2018-11-22 Google Llc Low latency matrix multiply unit
US10635740B2 (en) * 2017-05-17 2020-04-28 Google Llc Low latency matrix multiply unit
US10970362B2 (en) 2017-05-17 2021-04-06 Google Llc Low latency matrix multiply unit
US11500961B2 (en) 2017-05-17 2022-11-15 Google Llc Low latency matrix multiply unit
US11599601B2 (en) 2017-05-17 2023-03-07 Google Llc Low latency matrix multiply unit
US11907330B2 (en) 2017-05-17 2024-02-20 Google Llc Low latency matrix multiply unit
US11656849B2 (en) 2019-08-14 2023-05-23 Vorticity Inc. Dedicated hardware system for solving partial differential equations
US20220405060A1 (en) * 2019-08-19 2022-12-22 Vorticity Inc. Systolic array design for solving partial differential equations
US11640280B2 (en) * 2019-08-19 2023-05-02 Vorticity Inc. Systolic array design for solving partial differential equations

Also Published As

Publication number Publication date
EP0237571A4 (en) 1989-02-22
KR970001899B1 (en) 1997-02-18
DE3685107D1 (en) 1992-06-04
JPS63501530A (en) 1988-06-09
EP0237571B1 (en) 1992-04-29
WO1987001841A1 (en) 1987-03-26
EP0237571A1 (en) 1987-09-23
KR880011681A (en) 1988-10-29
US4922418A (en) 1990-05-01

Similar Documents

Publication Publication Date Title
US4720780A (en) Memory-linked wavefront array processor
Kung et al. Systolic arrays (for VLSI)
Kung et al. Wavefront array processor: Language, architecture, and applications
US5226171A (en) Parallel vector processing system for individual and broadcast distribution of operands and control information
Kung On supercomputing with systolic/wavefront array processors
US5659780A (en) Pipelined SIMD-systolic array processor and methods thereof
US4594655A (en) (k)-Instructions-at-a-time pipelined processor for parallel execution of inherently sequential instructions
US5410723A (en) Wavefront array processor for blocking the issuance of first handshake signal (req) by the presence of second handshake signal (ack) which indicates the readyness of the receiving cell
US5081573A (en) Parallel processing system
US4507748A (en) Associative processor with variable length fast multiply capability
US4821224A (en) Method and apparatus for processing multi-dimensional data to obtain a Fourier transform
US5319586A (en) Methods for using a processor array to perform matrix calculations
Sung et al. Parallel vlsi implementation of the kalrman filter
Buric et al. Bit-serial inner product processors in VLSI
CA1273711A (en) Memory-linked wavefront array processor
Taylor et al. An architecture for a video rate two-dimensional fast Fourier transform processor
WO2003092171A2 (en) Processing method and apparatus for implementing systolic arrays
JPH06223166A (en) General processor for image processing
Evans et al. Supercomputing with Data-Driven Wavefront Array Processors
Nash et al. VLSI implementation of a linear systolic array
Joshi et al. A video rate two dimensional FFT processor
Evans et al. The solution of linear systems by the QIF algorithm on a wavefront array processor
Schmidt et al. Wavefront array processor for video applications
Lawrie et al. Kalman filtering: A survey of parallel processing alternatives
RU1790786C (en) Device for matrix multiplication

Legal Events

Date Code Title Description
AS Assignment

Owner name: JOHNS HOPKINS UNIVERSITY THE, BALTIMORE, MARYLAND,

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST.;ASSIGNOR:DOLECEK, QUENTIN E.;REEL/FRAME:004465/0413

Effective date: 19850917

STCF Information on status: patent grant

Free format text: PATENTED CASE

FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY

FPAY Fee payment

Year of fee payment: 4

FEPP Fee payment procedure

Free format text: PAT HOLDER CLAIMS SMALL ENTITY STATUS - SMALL BUSINESS (ORIGINAL EVENT CODE: SM02); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY

FPAY Fee payment

Year of fee payment: 8

FEPP Fee payment procedure

Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY

FPAY Fee payment

Year of fee payment: 12